64 results on '"MNIST"'
Search Results
2. Hybrid SORN Hardware Accelerator for Support Vector Machines
- Author
-
Hülsmeier, Nils, Bärthel, Moritz, Rust, Jochen, Paul, Steffen, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Gustafson, John, editor, Leong, Siew Hoon, editor, and Michalewicz, Marek, editor
- Published
- 2023
- Full Text
- View/download PDF
3. Artificially Intelligent Readers: An Adaptive Framework for Original Handwritten Numerical Digits Recognition with OCR Methods.
- Author
-
Jain, Parth Hasmukh, Kumar, Vivek, Samuel, Jim, Singh, Sushmita, Mannepalli, Abhinay, and Anderson, Richard
- Subjects
- *
OPTICAL character recognition , *CONVOLUTIONAL neural networks , *DATA augmentation , *ARTIFICIAL intelligence - Abstract
Advanced artificial intelligence (AI) techniques have led to significant developments in optical character recognition (OCR) technologies. OCR applications, using AI techniques for transforming images of typed text, handwritten text, or other forms of text into machine-encoded text, provide a fair degree of accuracy for general text. However, even after decades of intensive research, creating OCR with human-like abilities has remained evasive. One of the challenges has been that OCR models trained on general text do not perform well on localized or personalized handwritten text due to differences in the writing style of alphabets and digits. This study aims to discuss the steps needed to create an adaptive framework for OCR models, with the intent of exploring a reasonable method to customize an OCR solution for a unique dataset of English language numerical digits were developed for this study. We develop a digit recognizer by training our model on the MNIST dataset with a convolutional neural network and contrast it with multiple models trained on combinations of the MNIST and custom digits. Using our methods, we observed results comparable with the baseline and provided recommendations for improving OCR accuracy for localized or personalized handwritten text. This study also provides an alternative perspective to generating data using conventional methods, which can serve as a gold standard for custom data augmentation to help address the challenges of scarce data and data imbalance. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
4. Data Generation with Variational Autoencoders and Generative Adversarial Networks †.
- Author
-
Devyatkin, Daniil and Trenev, Ivan
- Subjects
GENERATIVE adversarial networks ,PYTHON programming language ,DATA distribution ,PROBLEM solving ,DATA modeling - Abstract
The paper considers the problem of modelling the distribution of data with noise in the input data. In this paper, we consider encoders and decoders, which solve the problem of modelling data distribution. The improvement of variational autoencoders (VAEs) is discussed. Practical implementation is performed using the Python programming language and the Keras framework. Generative adversarial networks (GANs) and VAEs with noisy data are demonstrated. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
5. A Predictive Model of Handwritten Digits Recognition Using Expert Systems
- Author
-
Praveen, P., Abhishek, N., Reddy, K. Jayanth, Raj, C. Tanishq, Reddy, A. Yashwanth, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Ranganathan, G., editor, Fernando, Xavier, editor, Shi, Fuqian, editor, and El Allioui, Youssouf, editor
- Published
- 2022
- Full Text
- View/download PDF
6. Secure communication and implementation of handwritten digit recognition using deep neural network.
- Author
-
Alqahtani, Abdulrahman Saad, Madheswari, A. Neela, Mubarakali, Azath, and Parthasarathy, P.
- Subjects
- *
ARTIFICIAL neural networks , *DEEP learning , *MACHINE learning , *PATTERN recognition systems , *CONVOLUTIONAL neural networks , *SIGNAL processing - Abstract
Machine Learning is an important field of research in current trends. The extended field of machine learning is Deep Learning and is used for various research areas such as neural networks, image and signal processing, pattern recognition, etc. The handwritten digit recognition is an important task or process included in various applications such as car number plate recognition, staff identity number detection, etc. This paper proposed the design and analysis of various deep learning algorithms such as deep neural networks, convolutional neural networks, LeNet-5, AlexNet and MiniVGGNet for handwritten digit recognition using MNIST dataset. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
7. A convolutional neural network model of multi-scale feature fusion: MFF-Net.
- Author
-
Yi, Yunyun, Wang, Jinbao, Ding, Xingtao, and Li, Chenlong
- Subjects
- *
CONVOLUTIONAL neural networks , *MACHINE learning , *MULTISCALE modeling , *FEATURE extraction , *NEURAL circuitry - Abstract
MFF-Net (a multi-scale feature fusion convolutional neural network) was designed to improve the recognition rate of handwritten digits. The low-level, middle-level and high-level features of the image were first extracted through the convolution operation, and then the low-level and intermediate features were further extracted through different convolutional layers, later directly fused with the high-level features of the image with a certain weight, and then processed by the full connection layer. By adding a batch normalization layer before the activation layer, and a dropout layer between the full connection layers, the accuracy and generalization capacity of the network are improved. At the same time, a dynamic learning rate algorithm was designed, with which, the trained network accuracy was significantly improved as shown in the experiments on the MNIST data set. The accurate rate could reach 99.66% through only 30 epochs training. The comparison indicated that the accuracy of the network model is significantly higher than that of others. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
8. Reservoir Computing Using Autonomous Boolean Networks Realized on Field-Programmable Gate Arrays
- Author
-
Apostel, Stefan, Haynes, Nicholas D., Schöll, Eckehard, D’Huys, Otti, Gauthier, Daniel J., Bäck, Thomas, Series Editor, Kari, Lila, Series Editor, Nakajima, Kohei, editor, and Fischer, Ingo, editor
- Published
- 2021
- Full Text
- View/download PDF
9. Intelligent Arabic Handwriting Recognition Using Different Standalone and Hybrid CNN Architectures.
- Author
-
Albattah, Waleed and Albahli, Saleh
- Subjects
DEEP learning ,PATTERN recognition systems ,MACHINE learning ,HANDWRITING ,FEATURE extraction ,RECURRENT neural networks - Abstract
Handwritten character recognition is a computer-vision-system problem that is still critical and challenging in many computer-vision tasks. With the increased interest in handwriting recognition as well as the developments in machine-learning and deep-learning algorithms, researchers have made significant improvements and advances in developing English-handwriting-recognition methodologies; however, Arabic handwriting recognition has not yet received enough interest. In this work, several deep-learning and hybrid models were created. The methodology of the current study took advantage of machine learning in classification and deep learning in feature extraction to create hybrid models. Among the standalone deep-learning models trained on the two datasets used in the experiments performed, the best results were obtained with the transfer-learning model on the MNIST dataset, with 0.9967 accuracy achieved. The results for the hybrid models using the MNIST dataset were good, with accuracy measures exceeding 0.9 for all the hybrid models; however, the results for the hybrid models using the Arabic character dataset were inferior. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
10. Hierarchical Classification on the MNIST Dataset Using Truncated SVD and Kernel Density Estimation.
- Author
-
Plesovskaya, Ekaterina and Ivanov, Sergey
- Subjects
PROBABILITY density function ,CLASSIFICATION algorithms ,DENSITY ,MACHINE learning ,SINGULAR value decomposition ,SOURCE code ,ERROR rates - Abstract
The MNIST dataset is considered a challenging problem for machine learning algorithms. The present paper introduces a novel approach based on a truncated SVD and kernel density estimation that outputs an error rate on MNIST comparable to classical machine learning approaches. In addition to that, a hierarchical classification framework is proposed, that allows to enhance the algorithm accuracy. The resulting algorithm outperforms the reproducible SVM accuracy, which is regarded as a state-of-the-art machine learning algorithm for MNIST. The key advantage of the proposed framework consists in a lower computational cost: training on MNIST takes 142 times less and prediction takes 4 times less than for SVM on a single run. Thus, the research results state that TSVD-KDE algorithm has the potential for being an efficient classification algorithm. The source code for the experiment is released on GitHub: https://github.com/ekplesovskaya/MNIST-Classification-Using-TSVD-and-KDE. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
11. Inference with Artificial Neural Networks on Analog Neuromorphic Hardware
- Author
-
Weis, Johannes, Spilger, Philipp, Billaudelle, Sebastian, Stradmann, Yannik, Emmel, Arne, Müller, Eric, Breitwieser, Oliver, Grübl, Andreas, Ilmberger, Joscha, Karasenko, Vitali, Kleider, Mitja, Mauch, Christian, Schreiber, Korbinian, Schemmel, Johannes, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Gama, Joao, editor, Pashami, Sepideh, editor, Bifet, Albert, editor, Sayed-Mouchawe, Moamar, editor, Fröning, Holger, editor, Pernkopf, Franz, editor, Schiele, Gregor, editor, and Blott, Michaela, editor
- Published
- 2020
- Full Text
- View/download PDF
12. A Classical-Quantum Hybrid Approach for Unsupervised Probabilistic Machine Learning
- Author
-
Date, Prasanna, Schuman, Catherine, Patton, Robert, Potok, Thomas, Kacprzyk, Janusz, Series Editor, Arai, Kohei, editor, and Bhatia, Rahul, editor
- Published
- 2020
- Full Text
- View/download PDF
13. Data Generation with Variational Autoencoders and Generative Adversarial Networks
- Author
-
Daniil Devyatkin and Ivan Trenev
- Subjects
machine learning ,deep learning ,autoencoders ,generative adversarial network ,MNIST ,Engineering machinery, tools, and implements ,TA213-215 - Abstract
The paper considers the problem of modelling the distribution of data with noise in the input data. In this paper, we consider encoders and decoders, which solve the problem of modelling data distribution. The improvement of variational autoencoders (VAEs) is discussed. Practical implementation is performed using the Python programming language and the Keras framework. Generative adversarial networks (GANs) and VAEs with noisy data are demonstrated.
- Published
- 2023
- Full Text
- View/download PDF
14. Exploratory Analysis of MNIST Handwritten Digit for Machine Learning Modelling
- Author
-
Shamsuddin, Mohd Razif, Abdul-Rahman, Shuzlina, Mohamed, Azlinah, Barbosa, Simone Diniz Junqueira, Series Editor, Filipe, Joaquim, Series Editor, Kotenko, Igor, Series Editor, Sivalingam, Krishna M., Series Editor, Washio, Takashi, Series Editor, Yuan, Junsong, Series Editor, Zhou, Lizhu, Series Editor, Ghosh, Ashish, Series Editor, Yap, Bee Wah, editor, Mohamed, Azlinah Hj, editor, and Berry, Michael W., editor
- Published
- 2019
- Full Text
- View/download PDF
15. Handwritten Digit Recognition With Machine Learning Algorithms.
- Author
-
Demirkaya, Kübra Gülgün and Çavuşoğlu, Ünal
- Subjects
HANDWRITING recognition (Computer science) ,MACHINE learning ,INFORMATION retrieval ,DIGITAL media ,DEEP learning - Abstract
Nowadays, the scope of machine learning and deep learning studies is increasing day by day. Handwriting recognition is one of the examples in daily life for this field of work. Data storage in digital media is a method that almost everyone is using nowadays. At the same time, it has become a necessity for people to store their notes in digital media and even take notes directly in the digital environment. As a solution to this need, applications have been developed that can recognize numbers, characters, and even text from handwriting using machine learning and deep learning algorithms. Moreover, these applications can recognize numbers, characters, and text from handwriting and convert them into visual characters. This project, investigated the performance comparison of machine learning algorithms commonly used in handwriting recognition applications and which of them are more efficient. As a result of the study, the accuracy was 98.66% with artificial neural network, 99.45% with convolutional neural network, 97.05% with K-NN, 83.57% with Naive Bayes, 97.71% with support vector machine and 88.34% with decision tree. This study also developed a handwriting recognition system for numbers similar to these mentioned applications. A desktop application interface was developed for end users to show the instant performance of some of these algorithms and allow them to experience the handwriting recognition system. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
16. Analyze the effectiveness of an algorithm for identifying Polish characters in handwriting based on neural machine learning technologies.
- Author
-
Grzelak, Dawid, Podlaski, Krzysztof, and Wiatrowski, Grzegorz
- Subjects
ALGORITHMS ,MACHINE learning ,DEEP learning ,CONVOLUTIONAL neural networks ,HANDWRITING - Abstract
An approach is presented that generalize OCR task including polish letters using deep learning technique. The paper extends EMNIST dataset so that two new classes of polish diacritics "Ą" and "Ć" are attached. Using this new dataset and deep learning technique one can analyze sensitives of standard as well as presented extended approach with different parameters of convolutional neural network. The analysis of the results shows that the shadows and noises that Polish characters, leave with their hooks leads, can be properly recognized and two similar letters "A" and "Ą" can be distinguished by convolutional neural network. On the other hand a neural network trained on dataset without Polish characters do not treat letters "Ą" and "Ć" properly. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
17. Review and comparative analysis of machine learning libraries for machine learning
- Author
-
Migran N. Gevorkyan, Anastasia V. Demidova, Tatiana S. Demidova, and Anton A. Sobolev
- Subjects
machine learning ,neural networks ,mnist ,tensorflow ,pytorch ,Electronic computers. Computer science ,QA75.5-76.95 - Abstract
The article is an overview. We carry out the comparison of actual machine learning libraries that can be used the neural networks development. The first part of the article gives a brief description of TensorFlow, PyTorch, Theano, Keras, SciKit Learn libraries, SciPy library stack. An overview of the scope of these libraries and the main technical characteristics, such as performance, supported programming languages, the current state of development is given. In the second part of the article, a comparison of five libraries is carried out on the example of a multilayer perceptron, which is applied to the problem of handwritten digits recognizing. This problem is well known and well suited for testing different types of neural networks. The study time is compared depending on the number of epochs and the accuracy of the classifier. The results of the comparison are presented in the form of graphs of training time and accuracy depending on the number of epochs and in tabular form.
- Published
- 2019
- Full Text
- View/download PDF
18. Comparison of classical machine learning algorithms in the task of handwritten digits classification
- Author
-
Oleksandr Voloshchenko and Małgorzata Plechawska-Wójcik
- Subjects
machine learning ,classification ,MNIST ,classical algorithms ,Information technology ,T58.5-58.64 ,Electronic computers. Computer science ,QA75.5-76.95 - Abstract
The purpose of this paper is to compare classical machine learning algorithms for handwritten number classification. The following algorithms were chosen for comparison: Logistic Regression, SVM, Decision Tree, Random Forest and k-NN. MNIST handwritten digit database is used in the task of training and testing the above algorithms. The dataset consists of 70,000 images of numbers from 0 to 9. The algorithms are compared considering such criteria as the learning speed, prediction construction speed, host machine load, and classification accuracy. Each algorithm went through the training and testing phases 100 times, with the desired KPIs retained at each iteration. The results were averaged to reach reliable outcomes.
- Published
- 2021
- Full Text
- View/download PDF
19. Performance Analysis of Open Source Machine Learning Frameworks for Various Parameters in Single-Threaded and Multi-threaded Modes
- Author
-
Kochura, Yuriy, Stirenko, Sergii, Alienin, Oleg, Novotarskiy, Michail, Gordienko, Yuri, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Shakhovska, Natalia, editor, and Stepashko, Volodymyr, editor
- Published
- 2018
- Full Text
- View/download PDF
20. The Study of a Classification Technique for Numeric Gaze-Writing Entry in Hands-Free Interface
- Author
-
Sangbong Yoo, Dae Kyo Jeong, and Yun Jang
- Subjects
Gaze-writing ,input technique ,MNIST ,Eye tracking ,machine learning ,Electrical engineering. Electronics. Nuclear engineering ,TK1-9971 - Abstract
Recently, many applications are developed in numerous domains with various environments. Since some environments require hands-free applications, new technology is needed for the input interfaces other than the mouse and keyboard. Therefore, to meet the needs, many researchers have begun to investigate the gaze and voice for the input technology. In particular, there are many approaches to render virtual keyboards with the gaze. However, since the virtual keyboards hide the screen space, this technique can only be applied in limited environments. In this paper, we propose a classification technique for gaze-written numbers as the hands-free interface. Since the gaze-writing is less accurate compared to the virtual keyboard typing, we apply the convolutional neural network (CNN) deep learning algorithm to recognize the gaze-writing and improve the classification accuracy. Besides, we create new gaze-writing datasets for training, gaze MNIST (gMNIST), by modifying the MNIST data with features of the gaze movement patterns. For the evaluation, we compare our approach with the basic CNN structures using the original MNIST dataset. Our study will allow us to have more options for the input interfaces and expand our choices in hands-free environments.
- Published
- 2019
- Full Text
- View/download PDF
21. DIGI-Net: a deep convolutional neural network for multi-format digit recognition.
- Author
-
Madakannu, Arun and Selvaraj, Arivazhagan
- Subjects
- *
CONVOLUTIONAL neural networks , *ZIP codes , *RETINAL blood vessels , *MACHINE learning , *POSTAL codes , *CREDIT cards - Abstract
Digitizing different formats of digits has multiple applications like door number detection, license plate detection, credit card number detection, etc. Specifically, handwritten digit recognition has gained so much popularity because of the vast applications such as recognizing ZIP codes in postal documents, amount entered in check leafs, etc. The handwritten digits are not always of the similar size, width, orientation, as they differ because of different writing styles of the persons, different writing instruments, etc. This makes the recognition of handwritten digits a tough and tricky task. The main problem occurs during the classification of the digits of similarity such as 1 and 7, 5 and 6, 3 and 8, etc. Recognizing digits from unconstrained natural images are also relatively difficult because of its large appearance variability. Printed digit recognition has been virtually solved by machine learning researchers. This work does not focus on printed digit recognition, but aims to learn the features from printed digits to recognize handwritten and natural image digits better. In this work, we are proposing DIGI-Net, a deep convolutional network, which has the ability to learn common features from three different formats (handwritten, natural images, printed font) of digits and to recognize them. The experimentation is done on MNIST, CVL single digit dataset, digits of Chars74K dataset and our proposed DIGI-Net achieved an accuracy of 99.11%, 93.29% and 97.60% respectively. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
22. Object file system software experiments about the notion of number in humans and machines.
- Author
-
Bátfai, Norbert, Papp, Dávid, Bogacsovics, Gergő, Szabó, Máté, Simkó, Viktor Szilárd, Bersenszki, Márió, Szabó, Gergely, Kovács, Lajos, Kovács, Ferencz, and Varga, Erik Szilveszter
- Subjects
- *
SYSTEMS software , *ARTIFICIAL neural networks , *PSYCHOLOGICAL literature , *COMPUTER software , *DEEP learning - Abstract
In this paper, we present two types of software experiments, which were performed to study the numerosity classification (subitizing) in humans and machines. These experiments focus on the fields of subitizing and numerosity estimation, where the numerosity of objects placed in an image must be determined. The experiments called "SMNIST for Humans" are intended to measure the capacity of the Object File System (OFS) in humans. In this type of experiment, the measurement result is well in agreement with the value indicated in cognitive psychology literature. The experiments called "SMNIST for Machines" serve similar purposes but they investigate existing, well-known deep learning computer programs that are under development (and which were originally developed for other purposes). These measurement results can be interpreted similar to the results from "SMNIST for Humans". The main thesis of this paper can be formulated as follows: in machines, the image classification artificial neural networks can learn to distinguish numerosities with better accuracy when these numerosities are smaller than the capacity of OFS in humans. Finally, we outline a conceptual framework to investigate the notion of number in humans and machines. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
23. Introduction to convolutional neural network using Keras; an understanding from a statistician.
- Author
-
Hagyeong Lee and Jongwoo Song
- Subjects
NEURAL circuitry ,DEEP learning ,ARTIFICIAL intelligence - Abstract
Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
24. Artificially Intelligent Readers: An Adaptive Framework for Original Handwritten Numerical Digits Recognition with OCR Methods
- Author
-
Anderson, Parth Hasmukh Jain, Vivek Kumar, Jim Samuel, Sushmita Singh, Abhinay Mannepalli, and Richard
- Subjects
OCR ,adaptive ,custom ,digits ,MNIST ,informatics ,machine learning ,deep learning - Abstract
Advanced artificial intelligence (AI) techniques have led to significant developments in optical character recognition (OCR) technologies. OCR applications, using AI techniques for transforming images of typed text, handwritten text, or other forms of text into machine-encoded text, provide a fair degree of accuracy for general text. However, even after decades of intensive research, creating OCR with human-like abilities has remained evasive. One of the challenges has been that OCR models trained on general text do not perform well on localized or personalized handwritten text due to differences in the writing style of alphabets and digits. This study aims to discuss the steps needed to create an adaptive framework for OCR models, with the intent of exploring a reasonable method to customize an OCR solution for a unique dataset of English language numerical digits were developed for this study. We develop a digit recognizer by training our model on the MNIST dataset with a convolutional neural network and contrast it with multiple models trained on combinations of the MNIST and custom digits. Using our methods, we observed results comparable with the baseline and provided recommendations for improving OCR accuracy for localized or personalized handwritten text. This study also provides an alternative perspective to generating data using conventional methods, which can serve as a gold standard for custom data augmentation to help address the challenges of scarce data and data imbalance.
- Published
- 2023
- Full Text
- View/download PDF
25. A Limitation of Gradient Descent Learning.
- Author
-
Sum, John, Leung, Chi-Sing, and Ho, Kevin
- Subjects
- *
HANDWRITING recognition (Computer science) , *WEIGHT training , *MACHINE learning , *NOISE measurement - Abstract
Over decades, gradient descent has been applied to develop learning algorithm to train a neural network (NN). In this brief, a limitation of applying such algorithm to train an NN with persistent weight noise is revealed. Let $V({\mathbf w})$ be the performance measure of an ideal NN. $V({\mathbf w})$ is applied to develop the gradient descent learning (GDL). With weight noise, the desired performance measure (denoted as ${\mathcal{ J}}({\mathbf w})$) is $E[V(\tilde {\mathbf w})|{\mathbf w}]$ , where $\tilde {\mathbf w}$ is the noisy weight vector. Applying GDL to train an NN with weight noise, the actual learning objective is clearly not $V({\mathbf w})$ but another scalar function ${\mathcal{ L}}({\mathbf w})$. For decades, there is a misconception that ${\mathcal{ L}}({\mathbf w}) = {\mathcal{ J}}({\mathbf w})$ , and hence, the actual model attained by the GDL is the desired model. However, we show that it might not: 1) with persistent additive weight noise, the actual model attained is the desired model as ${\mathcal{ L}}({\mathbf w}) = {\mathcal{ J}}({\mathbf w})$ ; and 2) with persistent multiplicative weight noise, the actual model attained is unlikely the desired model as ${\mathcal{ L}}({\mathbf w}) \neq {\mathcal{ J}}({\mathbf w})$. Accordingly, the properties of the models attained as compared with the desired models are analyzed and the learning curves are sketched. Simulation results on 1) a simple regression problem and 2) the MNIST handwritten digit recognition are presented to support our claims. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
26. Nonlinear Activation Functions in CNN Based on Fluid Dynamics and Its Applications.
- Author
-
Kazuhiko Kakuda, Tomoyuki Enomoto, and Shinichiro Miura
- Subjects
NEURAL computers ,FLUID dynamics ,BIG data ,NUMERICAL analysis ,MACHINE learning - Abstract
The nonlinear activation functions in the deep CNN (Convolutional Neural Network) based on fluid dynamics are presented. We propose two types of activation functions by applying the so-called parametric softsign to the negative region. We use significantly the well-known TensorFlow as the deep learning framework. The CNN architecture consists of three convolutional layers with the max-pooling and one fullyconnected softmax layer. The CNN approaches are applied to three benchmark datasets, namely, MNIST, CIFAR-10, and CIFAR-100. Numerical results demonstrate the workability and the validity of the present approach through comparison with other numerical performances. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
27. Analysis of a hybrid quantum network for classification tasks
- Author
-
Gerhard Hellstern
- Subjects
tensorflow ,Quantum network ,Computer Networks and Communications ,Computer science ,business.industry ,finance ,TK5101-6720 ,quantum computing ,Theoretical Computer Science ,Computer Science Applications ,MNIST ,machine learning ,Computational Theory and Mathematics ,regularisation ,Telecommunication ,Artificial intelligence ,Electrical and Electronic Engineering ,business ,MNIST database ,Quantum computer - Abstract
In the era of noisy intermediate scaled quantum computers, one of the possible applications to search for an advantage of quantum computing is machine learning. Here, we report about an analysis, where a hybrid quantum‐classical network is applied to classify non‐trivial datasets (finance and MNIST data). In comparison to a pure classical network, we find an advantage when looking at several performance measures. As in classical machine learning, problems around overfitting the dataset arise. Therefore, we explore different possibilities to regularise the network.
- Published
- 2021
28. Adaptive high order stochastic descent algorithms
- Author
-
TURINICI, Gabriel
- Subjects
FMNIST ,adaptive step stochastic algorithm ,machine learning ,stochastic gradient descent ,stochastic Runge-Kutta ,CIFAR10 ,stochastic optimization ,artificial intelligence ,CIFAR100 ,MNIST - Abstract
Slides presented at the NANMATH 2022 conference, Cluj. Presentation abstract: motivated by statistical learning applications, the stochastic descent optimization algorithms are widely used today to tackle difficult numerical problems. One of the most known among them, the Stochastic Gradient Descent (SGD), has been extended in various ways resulting in Adam, Nesterov, momentum, etc. After a brief introduction to this framework, we introduce in this talk a new approach, called SGD-G2, which is a high order Runge-Kutta stochastic descent algorithm; the procedure allows for step adaptation in order to strike a optimal balance between convergence speed and stability. Numerical tests on standard datasets in machine learning are also presented together with further theoretical extensions.
- Published
- 2022
- Full Text
- View/download PDF
29. Histogram of Oriented Gradients in a Vision Transformer
- Author
-
Malmsten, Jakob, Cengiz, Heja, and Lood, David
- Subjects
hog ,machine learning ,ai ,histogram of oriented gradients ,artificial intelligence ,vision transformer ,vit ,Other Computer and Information Science ,Annan data- och informationsvetenskap ,MNIST - Abstract
This study aims to modify Vision Transformer (ViT) to achieve higher accuracy. ViT is a model used in computer vision to, among other things, classify images. By applying ViT to the MNIST data set, an accuracy of approximately 98% is achieved. ViT is modified by implementing a method called Histogram of Oriented Gradients (HOG) in two different ways. The results show that the first approach with HOG gives an accuracy of 98,74% (setup 1) and the second approach gives an accuracy of 96,87% (patch size 4x4 pixels). The study shows that when HOG is applied on the entire image, a better accuracy is obtained. However, no systematic optimization has taken place, which makes it difficult to draw conclusions with certainty.
- Published
- 2022
30. Building and Training a Fully Connected Deep Neural Network From Scratch
- Author
-
Berglund, Axel
- Subjects
Machine Learning ,MNIST ,Deep Neural Network ,Electrical Engineering, Electronic Engineering, Information Engineering ,Elektroteknik och elektronik ,Gradient Decent - Abstract
Artificial Neural Networks make up the core of mostMachine Learning algorithms. In the past decade Machine learninghave successfully taken on fields such as image recognition,Data analytics and medical technologies. As the area of usebecome less prone to mistakes, it raises the responsibility lookinto the black box of code and understand it to a deeper level. Inthis project, I built a Deep Neural Network from scratch, withouthigh level libraries, and trained it for a supervised classificationtask. The finished algorithm is flexible and can be adapted toany classification problem. The training method is based onBackpropagation and Gradient Descent. At last, the algorithmwas trained on the Modified National Institute of Standardsand Technology (MNIST) database, and performed with a 77%prediction acccuracy. There are a few optimization methods yetto be tested to further increase the performance. Artificiella neurala nätverk utgör kärnan i de flesta maskininlärningsalgoritmer idag. Under det senaste decenniet har maskininlärning framgångsrikt tagit an områden som bildigenkänning, dataanalys och medicinsk teknik. När användningsområdena blir mindre benägna till misstag, ökar ansvaret av att titta under huven och förstå den djupare nivåkoden. I denna studie var syftet att bygga ett djupt neuralt nätverk från grunden, utan högnivåbibliotek, och träna det för en övervakad klassificeringsuppgift. Den färdiga algoritmen är flexibel och kan designas för flera klassificeringsproblem. Nätverkets träningsmetod är baserad på Backpropagation och Gradient Descent. Valideringsdatan kunde till slut köras med 77% korrekt noggrannhet, och det finns finns ytterligare optimeringsmetoder att testa för att höja prestationen. Kandidatexjobb i elektroteknik 2022, KTH, Stockholm
- Published
- 2022
31. Review and comparative analysis of machine learning libraries for machine learning
- Author
-
Anton A. Sobolev, Tatiana S. Demidova, Anastasia V. Demidova, and Migran N. Gevorkyan
- Subjects
tensorflow ,mnist ,Artificial neural network ,business.industry ,Computer science ,Carry (arithmetic) ,Machine learning ,computer.software_genre ,neural networks ,lcsh:QA75.5-76.95 ,machine learning ,Multilayer perceptron ,Classifier (linguistics) ,pytorch ,Theano ,Artificial intelligence ,State (computer science) ,lcsh:Electronic computers. Computer science ,business ,computer ,MNIST database ,Scope (computer science) - Abstract
The article is an overview. We carry out the comparison of actual machine learning libraries that can be used the neural networks development. The first part of the article gives a brief description of TensorFlow, PyTorch, Theano, Keras, SciKit Learn libraries, SciPy library stack. An overview of the scope of these libraries and the main technical characteristics, such as performance, supported programming languages, the current state of development is given. In the second part of the article, a comparison of five libraries is carried out on the example of a multilayer perceptron, which is applied to the problem of handwritten digits recognizing. This problem is well known and well suited for testing different types of neural networks. The study time is compared depending on the number of epochs and the accuracy of the classifier. The results of the comparison are presented in the form of graphs of training time and accuracy depending on the number of epochs and in tabular form.
- Published
- 2019
32. Analysis of Fashion-MNIST benchmark suitability
- Author
-
Kondo, Masanori
- Subjects
MNISTデータ ,machine learning ,benchmark ,ベンチマーク ,機械学習 ,Fashion-MNIST ,ニューラルネットワーク ,neural networks ,MNIST - Abstract
application/pdf, 論文(Article), ニューラルネットワークの研究には20年に渡ってベンチマークの役割を担ってきたデータセットが存在し、世界中でニューラルネットワークの研究に使用されている。近年、第二のベンチマークを目指したデータセットが公開され人工知能研究に寄与しているが、両者の違いや学習の困難度等に関する評価が定まっていない。本稿では第二のデータセットと第一のデータセットの違いを検証し、将来の第三のデータセット構築のための手掛かりを模索する。, In the research of neural networks, one data set has played the benchmark role for 20 years, and it is currently used worldwide for such research. In recent years, a second data set has been published with the aim to create a second benchmark and contribute to artificial intelligence. However, the differences between the two data sets and difficulty in learning have not been established. In this paper, we examine the differences between the two data sets and explore the possibilities of constructing a third data set in the future.
- Published
- 2019
33. Relative stability toward diffeomorphisms indicates performance in deep nets*
- Author
-
Petrini, Leonardo, Favero, Alessandro, Geiger, Mario, and Wyart, Matthieu
- Subjects
FOS: Computer and information sciences ,Statistics and Probability ,Computer Science - Machine Learning ,mnist ,resnet ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,deep learning ,vgg ,Statistical and Nonlinear Physics ,Machine Learning (cs.LG) ,machine learning ,cifar10 ,alexnet ,features ,svhn ,Statistics, Probability and Uncertainty ,pretrained ,fashionmnist ,image classification - Abstract
Understanding why deep nets can classify data in large dimensions remains a challenge. It has been proposed that they do so by becoming stable to diffeomorphisms, yet existing empirical measurements support that it is often not the case. We revisit this question by defining a maximum-entropy distribution on diffeomorphisms, that allows to study typical diffeomorphisms of a given norm. We confirm that stability toward diffeomorphisms does not strongly correlate to performance on benchmark data sets of images. By contrast, we find that the stability toward diffeomorphisms relative to that of generic transformations $R_f$ correlates remarkably with the test error $\epsilon_t$. It is of order unity at initialization but decreases by several decades during training for state-of-the-art architectures. For CIFAR10 and 15 known architectures, we find $\epsilon_t\approx 0.2\sqrt{R_f}$, suggesting that obtaining a small $R_f$ is important to achieve good performance. We study how $R_f$ depends on the size of the training set and compare it to a simple model of invariant learning., Comment: NeurIPS 2021 Conference
- Published
- 2022
34. Reservoir Computing Using Autonomous Boolean Networks Realized on Field-Programmable Gate Arrays
- Author
-
Daniel J. Gauthier, Otti D'Huys, Nicholas D. Haynes, Stefan Apostel, and Eckehard Schöll
- Subjects
field-programmable gate array ,Computer science ,Topology (electrical circuits) ,Linear classifier ,01 natural sciences ,010305 fluids & plasmas ,MNIST ,Gate array ,recurrent network ,0103 physical sciences ,ddc:530 ,data classification ,010306 general physics ,Field-programmable gate array ,004 Datenverarbeitung ,Informatik ,business.industry ,Reservoir computing ,reservoir computing ,Network dynamics ,530 Physik ,autonomous Boolean networks ,network dynamics ,Boolean network ,machine learning ,phase transition ,Master clock ,ddc:004 ,business ,Computer hardware - Abstract
In this chapter, we consider realizing a reservoir computer on an electronic chip that allows for many tens of network nodes whose connection topology can be quickly reconfigured. The reservoir computer displays analog-like behavior and has the potential to perform computations beyond that of a classic Turning machine. In detail, we present our preliminary results of using a physical reservoir computer for performing the task of identifying written digits. The reservoir is realized on a commercially available electronic device known as a field-programmable gate array on which we create an autonomous Boolean network for information processing. Even though the network nodes are Boolean logic elements, they display analog behavior because there is no master clock that controls the nodes. In addition, the electronic signals related to the written-digit images are injected into the reservoir at high speed, leading to the possibility of full-image classification on the nanosecond time scale. We explore the dynamics of the autonomous Boolean networks in response to injected signals and, based on these results, investigate the performance of the reservoir computer on the written-digit task. For a wide range of reservoir structures, we obtain a typical performance of \(\sim \)90% for correctly identifying a written digit, which exceeds that obtained by a linear classifier. This work paves the way for achieving low-power, high-speed reservoir computing on readily available field-programmable gate arrays, which are well matched to existing computing infrastructure.
- Published
- 2021
- Full Text
- View/download PDF
35. Deep extreme learning machines: supervised autoencoding architecture for classification.
- Author
-
Tissera, Migel D. and McDonnell, Mark D.
- Subjects
- *
MACHINE learning , *COMPUTER algorithms , *CLASSIFICATION , *COMPUTER architecture , *CODING theory - Abstract
We present a method for synthesising deep neural networks using Extreme Learning Machines (ELMs) as a stack of supervised autoencoders. We test the method using standard benchmark datasets for multi-class image classification (MNIST, CIFAR-10 and Google Streetview House Numbers (SVHN)), and show that the classification error rate can progressively improve with the inclusion of additional autoencoding ELM modules in a stack. Moreover, we found that the method can correctly classify up to 99.19% of MNIST test images, which surpasses the best error rates reported for standard 3-layer ELMs or previous deep ELM approaches when applied to MNIST. The approach simultaneously offers a significantly faster training algorithm to achieve its best performance (in the order of 5 min on a four-core CPU for MNIST) relative to a single ELM with the same total number of hidden units as the deep ELM, hence offering the best of both worlds: lower error rates and fast implementation. [ABSTRACT FROM AUTHOR]
- Published
- 2016
- Full Text
- View/download PDF
36. Application of the FedAvg Algorithm in Remote Data Collection Systems
- Author
-
Jukica, Petar and Čavrak, Igor
- Subjects
Federated averaging ,TECHNICAL SCIENCES. Computing ,TEHNIČKE ZNANOSTI. Računarstvo ,Federativno učenje ,FedAvg ,ESP32 ,Strojno učenje ,MNIST ,Machine learning ,Federative learning - Abstract
Ovaj rad analizira potencijalne mogućnosti tehnike federativnog učenja, FedAvg, na uređajima ograničenih performansi. Pojašnjava se koncept federativnog učenja te se ukratko opisuju temeljne kategorije. Navode se mogući slučajevi uporabe federativnog učenja u razvoju stvarnih rješenja te problemi koje metoda rješava. Implementacija se odnosi na kategoriju horizontalnog federativnog učenja u kojoj je korišten ESP32 mikrokontroler za treniranje modela neuronske mreže nad skupom podataka MNIST. Razmatraju se rubni slučajevi te mogući problemi kod korištenja metode federativnog učenja. Rezultati eksperimenata su komentirani i navode se sljedeći koraci koji bi poboljšali postojeću implementaciju. This thesis analyses the potential capabilities and the use cases of federated learning method called federated averaging on the devices of extremely limited memory size and processing power. Federated learning concept is explained and its basic categories are briefly summarized. Possible use cases of federated learning are mentioned, as are the issues that could be mitigated with the use of its methods. ESP32 microcontroller was used in order to perform the training of the neural network model on the MNIST dataset. Edge cases of the generated federated averaging model were studied and possible issues were raised. Results of the experiments have been commented and next increments in the implementation of training algorithm have been proposed.
- Published
- 2021
37. Combining additive input noise annealing and pattern transformations for improved handwritten character recognition.
- Author
-
Alonso-Weber, J.M., Sesmero, M.P., and Sanchis, A.
- Subjects
- *
ARTIFICIAL neural networks , *BACK propagation , *SIMULATED annealing , *PATTERN recognition systems , *MACHINE learning ,WRITING - Abstract
Two problems that burden the learning process of Artificial Neural Networks with Back Propagation are the need of building a full and representative learning data set, and the avoidance of stalling in local minima. Both problems seem to be closely related when working with the handwritten digits contained in the MNIST dataset. Using a modest sized ANN, the proposed combination of input data transformations enables the achievement of a test error as low as 0.43%, which is up to standard compared to other more complex neural architectures like Convolutional or Deep Neural Networks. [ABSTRACT FROM AUTHOR]
- Published
- 2014
- Full Text
- View/download PDF
38. Neural network compression
- Author
-
Noguera Vall, Ferran, Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors, Ayguadé Parra, Eduard, and Llosa Espuny, José Francisco
- Subjects
Artificial intelligence ,aprenentatge profund ,xarxes neuronals convolutionals ,acceleració de xarxes neuronals ,capa densament connectada ,compressió de la matriu de pesos ,algoritmes de clustering ,arithmetic mean ,AlexNet ,MNIST ,Neural networks (Computer science) ,Machine learning ,convolutional neural networks ,Aprenentatge automàtic ,LeNet ,CIFAR-10 ,Xarxes neuronals (Informàtica) ,consum d'energia ,mitjana aritmètica ,clustering algorithms ,matrix compression ,ImageNet ,Intel·ligència artificial ,deep learning ,quantització ,neural networks ,neural network compression ,compressió de xarxes neuronals ,K-Means ,quantization ,fully-connected layer ,weight matrix compression - Abstract
In recent years, neural networks have grown in popularity, mostly thanks to the advances in the field of high performance computing. Nevertheless, some factors are still limiting the usage of neural networks. In particular, two limiting factors are storage requirements and computational cost. The aim of this project is to radically improve storage demand and provide direction for accelerating the execution of neural networks. In the scope of this thesis two compression algorithms have been developed. These algorithms share a common basis, both exploit error-tolerance is a property, because of this property the weight matrix can be divided into blocks simplifying the problem while merely impacting the accuracy. The first algorithm, groups the weights inside every block using different clustering techniques: Arithmetic mean and K-Means. To decide which clustering method to apply to which block standard deviation is employed among others. The user can specify a trade-off between accuracy and compression. This method has underperformed, obtaining a compression rate of 10,57 for AlexNet, which is not nearly state-of-the-art. The main issue is that meaningless weights are being merged with significant ones, causing a significant drop in the accuracy. The second algorithm, takes on the problem of accuracy loss by pruning all the unimportant weights. After pruning, quantization is applied. For both steps, pruning and quantization, two options have been explored which are effective for different kinds of neural networks. Of the possible combinations between pruning and quantization, one is selected by trial-and-error. The first pruning technique focuses on removing as many weights as possible, while the second pruning method considers blocks to a greater extend. The two types of quantization allow three values per block and five values per block respectively. This algorithm performed very well, obtaining a compression rate of 57,15 for AlexNet with minimal accuracy loss.
- Published
- 2021
39. LightLayers: Parameter Efficient Dense and Convolutional Layers for Image Classification
- Author
-
Dag Johansen, Pål Halvorsen, Michael Riegler, Håvard D. Johansen, Anis Yazidi, and Debesh Jha
- Subjects
FOS: Computer and information sciences ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,010103 numerical & computational mathematics ,010501 environmental sciences ,Machine learning ,computer.software_genre ,Kommunikasjon og distribuerte systemer: 423 [VDP] ,01 natural sciences ,Convolutional neural network ,Matrix decomposition ,MNIST ,CIFAR-10 ,0101 mathematics ,0105 earth and related environmental sciences ,Contextual image classification ,business.industry ,Deep learning ,Weight decomposition ,Lightweight models ,Communication and distributed systems: 423 [VDP] ,Face (geometry) ,Pattern recognition (psychology) ,Key (cryptography) ,Convolutional neural networks ,Artificial intelligence ,business ,computer ,MNIST database - Abstract
Deep Neural Networks (DNNs) have become the de-facto standard in computer vision, as well as in many other pattern recognition tasks. A key drawback of DNNs is that the training phase can be very computationally expensive. Organizations or individuals that cannot afford purchasing state-of-the-art hardware or tapping into cloud hosted infrastructures may face a long waiting time before the training completes or might not be able to train a model at all. Investigating novel ways to reduce the training time could be a potential solution to alleviate this drawback, and thus enabling more rapid development of new algorithms and models. In this paper, we propose LightLayers, a method for reducing the number of trainable parameters in deep neural networks (DNN). The proposed LightLayers consists of LightDense and LightConv2D layer that are as efficient as regular Conv2D and Dense layers, but uses less parameters. We resort to Matrix Factorization to reduce the complexity of the DNN models resulting into lightweight DNN models that require less computational power, without much loss in the accuracy. We have tested LightLayers on MNIST, Fashion MNIST, CIFAR 10, and CIFAR 100 datasets. Promising results are obtained for MNIST, Fashion MNIST, CIFAR-10 datasets whereas CIFAR 100 shows acceptable performance by using fewer parameters.
- Published
- 2021
40. Differentiable deformations for image classification models
- Author
-
Matanović, Pavo and Šegvić, Siniša
- Subjects
Deep Neural Networks ,thin-plate spline transformacija ,TEHNIČKE ZNANOSTI. Računarstvo ,Strojno učenje ,konvolucijske neuronske mreže ,Convolutional Neural Network ,duboke neuronske mreže ,clasification ,modul za prostornu transformaciju ,Affine transformation ,Thin-Plate Spline transformation ,klasifikacija ,MNIST ,afina transformacija ,Machine Learning ,Deep Learning ,TECHNICAL SCIENCES. Computing ,Spatial Transformer Network ,duboko učenje - Abstract
Rad daje uvod u umjetne neuronske mreže s naglaskom na konvolucijskim modelima. Ukratko je opisano učenje neuronske mreže. U radu uvodimo dodatni modul za prostornu transformaciju u konvolucijski model, kako bi poboljšali prostornu invarijantnost modela. Opisujemo arhitekturu dodatnog modula te dvije implementirane deformacije - afinu transformaciju i thin-plate spline transformaciju. Dana je programska implementacija modela te metode za učenje i evaluaciju istih. Modeli su trenirani na skupu MNIST. Prikazani su usporedni rezultati dvaju modela s modulom za prostornu transformaciju i modela bez dodatnog modula. This paper gives an introduction to artificial neural networks with emphasis on convolutional models. We described briefly learning process of neural network. In this work we introduce additional spatial transformer module in convolutional model to increase spatial invariance. We describe the architecture of additional module and two implemented deformations -- affine transformation and thin-plate spline transformation. This paper gives code of model in PyTorch and methods for training and testing models. We trained models on MNIST dataset. We gave comparative results of two models with spatial transformations and third model without STN.
- Published
- 2020
41. Tensor Deep Stacking Networks.
- Author
-
Hutchinson, Brian, Deng, Li, and Yu, Dong
- Subjects
- *
MACHINE learning , *VECTOR spaces , *PARAMETER estimation , *CENTRAL processing units , *PATTERN recognition systems , *TENSOR algebra - Abstract
A novel deep architecture, the tensor deep stacking network (T-DSN), is presented. The T-DSN consists of multiple, stacked blocks, where each block contains a bilinear mapping from two hidden layers to the output layer, using a weight tensor to incorporate higher order statistics of the hidden binary ($([0,1])$) features. A learning algorithm for the T-DSN's weight matrices and tensors is developed and described in which the main parameter estimation burden is shifted to a convex subproblem with a closed-form solution. Using an efficient and scalable parallel implementation for CPU clusters, we train sets of T-DSNs in three popular tasks in increasing order of the data size: handwritten digit recognition using MNIST (60k), isolated state/phone classification and continuous phone recognition using TIMIT (1.1 m), and isolated phone classification using WSJ0 (5.2 m). Experimental results in all three tasks demonstrate the effectiveness of the T-DSN and the associated learning methods in a consistent manner. In particular, a sufficient depth of the T-DSN, a symmetry in the two hidden layers structure in each T-DSN block, our model parameter learning algorithm, and a softmax layer on top of T-DSN are shown to have all contributed to the low error rates observed in the experiments for all three tasks. [ABSTRACT FROM PUBLISHER]
- Published
- 2013
- Full Text
- View/download PDF
42. Efficient and effective algorithms for training single-hidden-layer neural networks
- Author
-
Yu, Dong and Deng, Li
- Subjects
- *
COMPUTER algorithms , *ARTIFICIAL neural networks , *MACHINE learning , *GAMMA ray telescopes , *COMPARATIVE studies , *PATTERN perception - Abstract
Abstract: Recently there have been renewed interests in single-hidden-layer neural networks (SHLNNs). This is due to its powerful modeling ability as well as the existence of some efficient learning algorithms. A prominent example of such algorithms is extreme learning machine (ELM), which assigns random values to the lower-layer weights. While ELM can be trained efficiently, it requires many more hidden units than is typically needed by the conventional neural networks to achieve matched classification accuracy. The use of a large number of hidden units translates to significantly increased test time, which is more valuable than training time in practice. In this paper, we propose a series of new efficient learning algorithms for SHLNNs. Our algorithms exploit both the structure of SHLNNs and the gradient information over all training epochs, and update the weights in the direction along which the overall square error is reduced the most. Experiments on the MNIST handwritten digit recognition task and the MAGIC gamma telescope dataset show that the algorithms proposed in this paper obtain significantly better classification accuracy than ELM when the same number of hidden units is used. For obtaining the same classification accuracy, our best algorithm requires only 1/16 of the model size and thus approximately 1/16 of test time compared with ELM. This huge advantage is gained at the expense of 5 times or less the training cost incurred by the ELM training. [Copyright &y& Elsevier]
- Published
- 2012
- Full Text
- View/download PDF
43. Увеличение объема данных обучения и бустинг сверточных нейронных сетей для снижения уровня ошибок набора данных MNIST
- Author
-
Romanuke, Vadim V.
- Subjects
Boosting (machine learning) ,boosting ,Computer science ,convolutional neural network ,Word error rate ,error rate ,02 engineering and technology ,бустинг ,Machine learning ,computer.software_genre ,Convolutional neural network ,MNIST ,уровень ошибок ,0202 electrical engineering, electronic engineering, information engineering ,Training set ,увеличение объема данных обучения ,згорткова нейронна мережа ,business.industry ,збільшення обсягу даних навчання ,020206 networking & telecommunications ,Pattern recognition ,General Medicine ,training data expansion ,сверточная нейронная сеть ,519.226+004.852 ,020201 artificial intelligence & image processing ,рівень помилок ,Artificial intelligence ,Performance improvement ,business ,computer ,MNIST database - Abstract
Проблематика. Оскільки попередні підходи до покращення рівня помилок банку зображень MNIST не мають чіткої структури, яка могла би бути чітко відтворена, розглядається формалізація покращення продуктивності. Мета дослідження. Метою роботи є строга формалізація стратегії зниження рівня помилок банку даних MNIST. Методика реалізації. Пропонується алгоритм досягнення кращої продуктивності за допомогою збільшення обсягу даних навчання та бустингу. Алгоритм використовує розроблену концепцію збільшення обсягу даних навчання. Координація цієї концепції та алгоритму визначає стратегію зниження рівня помилок. Результати дослідження. У відносному порівнянні продуктивність однієї згорткової нейронної мережі на банку даних MNIST покращена майже на 30 %. За допомогою бустингу продуктивність становить 0,21 % – не розпізнається лише 21 рукописна цифра з 10000. Висновки. Збільшення обсягу даних навчання є визначальним для зниження рівня помилок банку даних MNIST. Без цього бустинг неефективний. Застосування викладеного підходу має виразний вплив на зниження рівня помилок банку даних MNIST при використанні лише 5 або 6 згорткових нейронних мереж проти 35 в еталонній роботі. Background. Due to that the preceding approaches for improving the MNIST image dataset error rate do not have a clear structure which could let repeat it in a strengthened manner, the formalization of the performance improvement is considered. Objective. The goal is to strictly formalize a strategy of reducing the MNIST dataset error rate. Methods. An algorithm for achieving the better performance by expanding the training data and boosting with ensembles is suggested. The algorithm uses the designed concept of the training data expansion. Coordination of the concept and the algorithm defines a strategy of the error rate reduction. Results. In relative comparison, the single convolutional neural network performance on the MNIST dataset has been bettered almost by 30 %. With boosting, the performance is 0.21 % error rate meaning that only 21 handwritten digits from 10,000 are not recognized. Conclusions. The training data expansion is crucial for reducing the MNIST dataset error rate. The boosting is ineffective without it. Application of the stated approach has an impressive impact for reducing the MNIST dataset error rate, using only 5 or 6 convolutional neural networks against those 35 ones in the benchmark work. Проблематика. Поскольку предыдущие подходы к улучшению уровня ошибок набора данных MNIST не имеют четкой структуры, которая могла бы быть четко воссоздана, рассматривается формализация улучшения производительности. Цель исследования. Целью работы является строгая формализация стратегии снижения уровня ошибок набора данных MNIST. Методика реализации. Предлагается алгоритм достижения лучшей производительности с помощью увеличения объема данных обучения и бустинга. Алгоритм использует разработанную концепцию увеличения объема данных обучения. Координация этой концепции и алгоритма определяет стратегию снижения уровня ошибок. Результаты исследования. В относительном сравнении производительность одной сверточной нейронной сети на наборе данных MNIST улучшена почти на 30 %. С помощью бустинга производительность составляет 0,21 % – не распознается лишь 21 рукописная цифра из 10000. Выводы. Увеличение объема данных обучения является определяющим для снижения уровня ошибок. Без этого бустинг неэффективен. Применение изложенного подхода оказывает выразительное влияние на снижение уровня ошибок набора данных MNIST при использовании лишь 5 или 6 сверточных нейронных сетей против 35 в эталонной работе.
- Published
- 2016
44. IMPLEMENTASI DAN ANALISA JARINGAN SARAF TIRUAN DENGAN FEATURE NORMALIZATION DAN PRINCIPAL COMPONENT ANALYSIS UNTUK DIGIT CLASSIFIER
- Author
-
Wahid, Nur Abdul, Sarwo, Sarwo, and Setiawan, Adi Wahyu
- Subjects
pca ,mnist ,machine learning ,normalisasi fitur ,pengenal angka ,feedforward ,klasifikasi ,jaringan saraf tiruan - Abstract
Digit classifier yang dikembangkan, digunakan untuk mengklasifikasikan angka dari tulisantangan. Sudah banyak sekali digit classifier yang dikembangkan dengan berbagai algoritmamachine learning, salah satu yang populer dan terus berkembang adalah jaringan saraf tiruan.Dengan motivasi tersebut, penulis juga membangun digit classifier menggunakan jaringan saraftiruan yang dipadukan dengan teknik optimisasi. Jenis arsitektur jaringan saraf tiruan yang akandigunakan adalah feedforward dan back propagation. Teknik optimisasi feature normalization danprincipal component analysis (PCA) juga akan digunakan untuk meningkatkan performa model.Set data yang digunakan untuk melatih model merupakan data Mixed National Institute ofStandards and Technology (MNIST). Dengan memadukan jaringan saraf tiruan dan teknik-teknikoptimisasi tersebut diharapkan dapat meningkatkan performa dan akurasi untukmengklasifikasikan angka serta memberikan pemahaman baru bagi penulis.
- Published
- 2019
45. Automatic, Qualitative Scoring of the Clock Drawing Test (CDT) Based on U-Net, CNN and Mobile Sensor Data.
- Author
-
Park, Ingyu and Lee, Unjoo
- Subjects
- *
DEEP learning , *IMAGE databases , *SMART devices , *MACHINE learning , *COGNITIVE ability , *IMAGE segmentation , *DETECTORS , *IMAGE sensors - Abstract
The Clock Drawing Test (CDT) is a rapid, inexpensive, and popular screening tool for cognitive functions. In spite of its qualitative capabilities in diagnosis of neurological diseases, the assessment of the CDT has depended on quantitative methods as well as manual paper based methods. Furthermore, due to the impact of the advancement of mobile smart devices imbedding several sensors and deep learning algorithms, the necessity of a standardized, qualitative, and automatic scoring system for CDT has been increased. This study presents a mobile phone application, mCDT, for the CDT and suggests a novel, automatic and qualitative scoring method using mobile sensor data and deep learning algorithms: CNN, a convolutional network, U-Net, a convolutional network for biomedical image segmentation, and the MNIST (Modified National Institute of Standards and Technology) database. To obtain DeepC, a trained model for segmenting a contour image from a hand drawn clock image, U-Net was trained with 159 CDT hand-drawn images at 128 × 128 resolution, obtained via mCDT. To construct DeepH, a trained model for segmenting the hands in a clock image, U-Net was trained with the same 159 CDT 128 × 128 resolution images. For obtaining DeepN, a trained model for classifying the digit images from a hand drawn clock image, CNN was trained with the MNIST database. Using DeepC, DeepH and DeepN with the sensor data, parameters of contour (0–3 points), numbers (0–4 points), hands (0–5 points), and the center (0–1 points) were scored for a total of 13 points. From 219 subjects, performance testing was completed with images and sensor data obtained via mCDT. For an objective performance analysis, all the images were scored and crosschecked by two clinical experts in CDT scaling. Performance test analysis derived a sensitivity, specificity, accuracy and precision for the contour parameter of 89.33, 92.68, 89.95 and 98.15%, for the hands parameter of 80.21, 95.93, 89.04 and 93.90%, for the numbers parameter of 83.87, 95.31, 87.21 and 97.74%, and for the center parameter of 98.42, 86.21, 96.80 and 97.91%, respectively. From these results, the mCDT application and its scoring system provide utility in differentiating dementia disease subtypes, being valuable in clinical practice and for studies in the field. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
46. Deep extreme learning machines: supervised autoencoding architecture for classification
- Author
-
Migel D. Tissera, Mark D. McDonnell, Tissera, Migel D, and McDonnell, Mark D
- Subjects
0209 industrial biotechnology ,Computer science ,Cognitive Neuroscience ,Word error rate ,extreme learningmachine ,02 engineering and technology ,Machine learning ,computer.software_genre ,supervised learning ,MNIST ,020901 industrial engineering & automation ,Artificial Intelligence ,0202 electrical engineering, electronic engineering, information engineering ,classifier ,Extreme learning machine ,autoencoder ,Contextual image classification ,business.industry ,Supervised learning ,deep neural network ,Pattern recognition ,Autoencoder ,Computer Science Applications ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,computer ,MNIST database - Abstract
We present a method for synthesising deep neural networks using Extreme Learning Machines (ELMs) as a stack of supervised autoencoders. We test the method using standard benchmark datasets for multi-class image classification (MNIST, CIFAR-10 and Google Streetview House Numbers (SVHN)), and show that the classification error rate can progressively improve with the inclusion of additional autoencoding ELM modules in a stack. Moreover, we found that the method can correctly classify up to 99.19% of MNIST test images, which surpasses the best error rates reported for standard 3-layer ELMs or previous deep ELM approaches when applied to MNIST. The approach simultaneously offers a significantly faster training algorithm to achieve its best performance (in the order of 5. min on a four-core CPU for MNIST) relative to a single ELM with the same total number of hidden units as the deep ELM, hence offering the best of both worlds: lower error rates and fast implementation. Refereed/Peer-reviewed
- Published
- 2016
47. Character Recognition Using TensorFlow Library
- Author
-
Vodopija, Andreja and Pribanić, Tomislav
- Subjects
optical character recognition ,TensorFlow ,logistic regression ,TEHNIČKE ZNANOSTI. Računarstvo ,softmax regresija ,softmax regression ,hyperparameters ,strojno učenje ,MNIST ,hiperparametri ,machine learning ,logistička regresija ,TECHNICAL SCIENCES. Computing ,umjetna neuronska mreža ,optičko prepoznavanje znakova ,artificial neural network - Abstract
Postoje 3 vrste strojnog učenja: nadzirano, nenadzirano i podržano učenje. U ovom radu su opisane 3 metode nadziranog učenja: logistička regresija, softmax regresija i umjetne neuronske mreže. Logistička regresija služi za binarnu klasifikaciju, dok softmax regresija služi za višeklasnu klasifikaciju. S obzirom da ne daju dobre rezultate za linearno neodvojive probleme, takvi problemi se mogu rješavati umjetnim neuronskim mrežama zahvaljujući njenim skrivenim slojevima. Optičko prepoznavanje znakova implementirano je umjetnom neuronskom mrežom te se pri tome korisi biblotekom TensorFlow i podatcima iz baze MNIST. Veliku ulogu u treniranju umjetne neuronske mreže imaju takozvani hiperparametri: stopa učenja, veličina uzorka i broj epoha. Rezultati točnosti uvelike ovise o hiperparametrima mreže. There are 3 types of machine learning: supervised, unsupervised and reinforcement learning. In this thesis are explained 3 methods of supervised learning: logistic regression, softmax regression and artificial neural networks. Logistic regression is used for binary classification while softmax is used for multiclass classification. These methods don't offer good results for linearly unseparable problems where artificial neural networks can be used thanks to their hidden-layers. Optical character recognition is implemented with neural networks and uses TensorFlow library and MNIST database. Hyperparameters play huge role in training and accuracy of a neural networks. Parameters that have been studied in this thesis are learning rate, batch size and number of epochs.
- Published
- 2018
48. Image Classification With Deep Convolutional Models With Residual Connections
- Author
-
Borac, Antonio and Šegvić, Siniša
- Subjects
TEHNIČKE ZNANOSTI. Računarstvo ,deep convolutional residual models ,neural networks ,duboki konvolucijski rezidualni modeli ,strojno učenje ,MNIST ,klasifikacija slika ,Tensorflow ,machine learning ,TECHNICAL SCIENCES. Computing ,neuronske mreže ,PyTorch ,CIFAR10 ,image classification - Abstract
Klasifikacija slika prirodnih scena je neriješen problem računalnog vida s mnogim zanimljivim primjenama. U posljednje vrijeme najbolji rezultati u tom području postižu se pristupima utemeljenima na dubokim konvolucijskim modelima. Za ovaj rad posebno su zanimljivi nadzirani pristupi gdje je svaka slika skupa za učenje označena semantičkim razredima objekata koje slika sadrži. U okviru rada, bilo je potrebno proučiti dokumentacije programskih okvira Tensorflow i PyTorch te biblioteke programskog jezika Python za rukovanje matricama i slikama. Izrađena je izvedba programskog sustava za učenje i primjenu klasifikacijskog modela. Evaluiran je utjecaj rezidualnih veza na točnost modela. Detaljno su analizirane konvolucijske mreže u okviru dubokog učenja. Prikazani su i ocijenjeni ostvareni rezultati i predložene izmjene za poboljšanje rezultata. Image classification of natural scenes is an unsolved problem of computer vision with many interesting applications. Recently, approaches with deep convolutional models achieve best results in that area. For this paper were specially interesting supervised approaches where every image from training set is labeled with semantic classes of objects which image contains. In this paper documentations of programming frameworks Tensorflow and PyTorch for matrix and image handling were studied. Implementation of programming system for learning and application of classification model have been done. Implact of residual connections on model accuracy have been evaluated. Convolutional networks were deeply analized in context of deep learning. Achieved results have been shown and evaluated and suggestions for classification accuracy improvment have been provided.
- Published
- 2018
49. Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms
- Author
-
Thomas Sikora, Tobias Senst, and Erik Bochinski
- Subjects
Hyperparameter ,Image Classification ,business.industry ,Computer science ,020208 electrical & electronic engineering ,Evolutionary Algorithm ,Evolutionary algorithm ,Convolutional Neural Network ,02 engineering and technology ,Machine learning ,computer.software_genre ,Convolutional neural network ,Hyper-parameter Optimization ,Evolutionary computation ,MNIST ,Kernel (image processing) ,Evolutionary acquisition of neural topologies ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,computer ,MNIST database - Abstract
In a broad range of computer vision tasks, convolutional neural networks (CNNs) are one of the most prominent techniques due to their outstanding performance. Yet it is not trivial to find the best performing network structure for a specific application because it is often unclear how the network structure relates to the network accuracy. We propose an evolutionary algorithm-based framework to automatically optimize the CNN structure by means of hyper-parameters. Further, we extend our framework towards a joint optimization of a committee of CNNs to leverage specialization and cooperation among the individual networks. Experimental results show a significant improvement over the state-of-the-art on the well-established MNIST dataset for hand-written digits recognition.
- Published
- 2017
50. An energy efficient additive neural network
- Author
-
Arman Afrasiyabi, Ozan Yildiz, A. Enis Cetin, Fatos T. Yarman Vural, Baris Nasir, and Çetin, A. Enis
- Subjects
Artificial intelligence ,Theoretical computer science ,Computer Science::Neural and Evolutionary Computation ,02 engineering and technology ,Lebesgue integrable functions ,Probabilistic neural network ,Machine learning ,0202 electrical engineering, electronic engineering, information engineering ,Universal approximation properties ,Stochastic neural network ,Efficient ANN ,Mnist ,Mathematics ,Multiplierless ann ,Learning systems ,Artificial neural network ,Time delay neural network ,Euclidean space ,020206 networking & telecommunications ,Perceptron ,Norm (mathematics) ,XOR ,020201 artificial intelligence & image processing ,Algorithm ,Energy efficient ,Neural networks ,MNIST database - Abstract
Date of Conference: 15-18 May 2017 Conference Name: IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017 In this paper, we propose a new energy efficient neural network with the universal approximation property over space of Lebesgue integrable functions. This network, called additive neural network, is very suitable for mobile computing. The neural structure is based on a novel vector product definition, called ef-operator, that permits a multiplier-free implementation. In ef-operation, the 'product' of two real numbers is defined as the sum of their absolute values, with the sign determined by the sign of the product of the numbers. This 'product' is used to construct a vector product in n-dimensional Euclidean space. The vector product induces the lasso norm. The proposed additive neural network successfully solves the XOR problem. The experiments on MNIST dataset show that the classification performances of the proposed additive neural networks are very similar to the corresponding multi-layer perceptron.
- Published
- 2017
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.