Search

Learning in neural networks with locally-tuned neuron models such as radial Basis Function (RBF) networks is often seen as instable, in particular when multi-layered architectures are used. Furthermore, universal approximation theorems for single-layered RBF networks are very well established; therefore, deeper architectures are theoretically not required. Consequently, RBFs are mostly used in a single-layered manner. However, deep neural networks have proven their effectiveness on many different tasks. In this paper, we show that deeper RBF architectures with multiple radial basis function layers can be designed together with efficient learning schemes. We introduce an initialization scheme for deep RBF networks based on k-means clustering and covariance estimation. We further show how to make use of convolutions to speed up the calculation of the Mahalanobis distance in a partially connected way, which is similar to the convolutional neural networks (CNNs). Finally, we evaluate our approach on image classification as well as speech emotion recognition tasks. Our results show that deep RBF networks perform very well, with comparable results to other deep neural network types, such as CNNs. [ABSTRACT FROM AUTHOR]

Recent studies on watermarking techniques based on image carriers have demonstrated new approaches that combine adversarial perturbations against steganalysis with embedding distortions. However, while these methods successfully counter convolutional neural network-based steganalysis, they do not adequately protect the data of the carrier itself. Recognizing the high sensitivity of Deep Neural Networks (DNNs) to small perturbations, we propose HAG-NET, a method based on image carriers, which is jointly trained by the encoder, decoder, and attacker. In this paper, the encoder generates Adversarial Steganographic Examples (ASEs) that are adversarial to the target classification network, thereby providing protection for the carrier data. Additionally, the decoder can recover secret data from ASEs. The experimental results demonstrate that ASEs produced by HAG-NET achieve an average success rate of over 99% on both the MNIST and CIFAR-10 datasets. ASEs generated with the attacker exhibit greater robustness in terms of attack ability, with an average increase of about 3.32%. Furthermore, our method, when compared with other generative stego examples under similar perturbation strength, contains significantly more information according to image information entropy measurements. [ABSTRACT FROM AUTHOR]

In image classification with Deep Convolutional Neural Networks (DCNNs), the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Existing studies demonstrated that a subnetwork can replace pointwise convolutional layers with significantly fewer parameters and fewer floating-point computations, while maintaining the learning capacity. In this paper, we propose an improved scheme for reducing the complexity of pointwise convolutions in DCNNs for image classification based on interleaved grouped filters without divisibility constraints. The proposed scheme utilizes grouped pointwise convolutions, in which each group processes a fraction of the input channels. It requires a number of channels per group as a hyperparameter C h . The subnetwork of the proposed scheme contains two consecutive convolutional layers K and L, connected by an interleaving layer in the middle, and summed at the end. The number of groups of filters and filters per group for layers K and L is determined by exact divisions of the original number of input channels and filters by C h . If the divisions were not exact, the original layer could not be substituted. In this paper, we refine the previous algorithm so that input channels are replicated and groups can have different numbers of filters to cope with non exact divisibility situations. Thus, the proposed scheme further reduces the number of floating-point computations (11%) and trainable parameters (10%) achieved by the previous method. We tested our optimization on an EfficientNet-B0 as a baseline architecture and made classification tests on the CIFAR-10, Colorectal Cancer Histology, and Malaria datasets. For each dataset, our optimization achieves a saving of 76%, 89%, and 91% of the number of trainable parameters of EfficientNet-B0, while keeping its test classification accuracy. [ABSTRACT FROM AUTHOR]

A new trend in deep learning, represented by Mutual Information Neural Estimation (MINE) and Information Noise Contrast Estimation (InfoNCE), is emerging. In this trend, similarity functions and Estimated Mutual Information (EMI) are used as learning and objective functions. Coincidentally, EMI is essentially the same as Semantic Mutual Information (SeMI) proposed by the author 30 years ago. This paper first reviews the evolutionary histories of semantic information measures and learning functions. Then, it briefly introduces the author's semantic information G theory with the rate-fidelity function R(G) (G denotes SeMI, and R(G) extends R(D)) and its applications to multi-label learning, the maximum Mutual Information (MI) classification, and mixture models. Then it discusses how we should understand the relationship between SeMI and Shannon's MI, two generalized entropies (fuzzy entropy and coverage entropy), Autoencoders, Gibbs distributions, and partition functions from the perspective of the R(G) function or the G theory. An important conclusion is that mixture models and Restricted Boltzmann Machines converge because SeMI is maximized, and Shannon's MI is minimized, making information efficiency G/R close to 1. A potential opportunity is to simplify deep learning by using Gaussian channel mixture models for pre-training deep neural networks' latent layers without considering gradients. It also discusses how the SeMI measure is used as the reward function (reflecting purposiveness) for reinforcement learning. The G theory helps interpret deep learning but is far from enough. Combining semantic information theory and deep learning will accelerate their development. [ABSTRACT FROM AUTHOR]

A major issue in the application of deep learning is the definition of a proper architecture for the learning machine at hand, in such a way that the model is neither excessively large (which results in overfitting the training data) nor too small (which limits the learning and modeling capabilities of the automatic learner). Facing this issue boosted the development of algorithms for automatically growing and pruning the architectures as part of the learning process. The paper introduces a novel approach to growing the architecture of deep neural networks, called downward-growing neural network (DGNN). The approach can be applied to arbitrary feed-forward deep neural networks. Groups of neurons that negatively affect the performance of the network are selected and grown with the aim of improving the learning and generalization capabilities of the resulting machine. The growing process is realized via replacement of these groups of neurons with sub-networks that are trained relying on ad hoc target propagation techniques. In so doing, the growth process takes place simultaneously in both the depth and width of the DGNN architecture. We assess empirically the effectiveness of the DGNN on several UCI datasets, where the DGNN significantly improves the average accuracy over a range of established deep neural network approaches and over two popular growing algorithms, namely, the AdaNet and the cascade correlation neural network. [ABSTRACT FROM AUTHOR]

With the remarkable development of deep learning in the field of science, deep neural networks provide a new way to solve the Stefan problem. In this paper, deep neural networks combined with small sample learning and a general deep learning framework are proposed to solve the two-dimensional Stefan problem. In the case of adding less sample data, the model can be modified and the prediction accuracy can be improved. In addition, by solving the forward and inverse problems of the two-dimensional single-phase Stefan problem, it is verified that the improved method can accurately predict the solutions of the partial differential equations of the moving boundary and the dynamic interface. [ABSTRACT FROM AUTHOR]

As a promising information theory, reinforcement learning has gained much attention. This paper researches a wind-storage cooperative decision-making strategy based on dueling double deep Q-network (D3QN). Firstly, a new wind-storage cooperative model is proposed. Besides wind farms, energy storage systems, and external power grids, demand response loads are also considered, including residential price response loads and thermostatically controlled loads (TCLs). Then, a novel wind-storage cooperative decision-making mechanism is proposed, which combines the direct control of TCLs with the indirect control of residential price response loads. In addition, a kind of deep reinforcement learning algorithm called D3QN is utilized to solve the wind-storage cooperative decision-making problem. Finally, the numerical results verify the effectiveness of D3QN for optimizing the decision-making strategy of a wind-storage cooperation system. [ABSTRACT FROM AUTHOR]

Electrical impedance tomography (EIT) is a non-invasive imaging modality used for estimating the conductivity of an object Ω from boundary electrode measurements. In recent years, researchers achieved substantial progress in analytical and numerical methods for the EIT inverse problem. Despite the success, numerical instability is still a major hurdle due to many factors, including the discretization error of the problem. Furthermore, most algorithms with good performance are relatively time consuming and do not allow real-time applications. In our approach, the goal is to separate the unknown conductivity into two regions, namely the region of homogeneous background conductivity and the region of non-homogeneous conductivity. Therefore, we pose and solve the problem of shape reconstruction using machine learning. We propose a novel and simple jet intriguing neural network architecture capable of solving the EIT inverse problem. It addresses previous difficulties, including instability, and is easily adaptable to other ill-posed coefficient inverse problems. That is, the proposed model estimates the probability for a point of whether the conductivity belongs to the background region or to the non-homogeneous region on the continuous space R d ∩ Ω with d ∈ { 2 , 3 } . The proposed model does not make assumptions about the forward model and allows for solving the inverse problem in real time. The proposed machine learning approach for shape reconstruction is also used to improve gradient-based methods for estimating the unknown conductivity. In this paper, we propose a piece-wise constant reconstruction method that is novel in the inverse problem setting but inspired by recent approaches from the 3D vision community. We also extend this method into a novel constrained reconstruction method. We present extensive numerical experiments to show the performance of the architecture and compare the proposed method with previous analytic algorithms, mainly the monotonicity-based shape reconstruction algorithm and iteratively regularized Gauss–Newton method. [ABSTRACT FROM AUTHOR]

Machine learning (ML) has achieved remarkable success in a wide range of applications. In recent ML research, deep anomaly detection (AD) has been a hot topic with the aim of discriminating among anomalous data with deep neural networks (DNNs). Notably, image AD is one of the most representative tasks in current deep AD research. ML's interaction with quantum computing is giving rise to a heated topic named quantum machine learning (QML), which enjoys great prospects according to recent academic research. This paper attempts to address the image AD problem in a deep manner with a novel QML solution. Specifically, we design a quantum-classical hybrid DNN (QHDNN) that aims to learn directly from normal raw images to train a normality model and then exclude images that do not conform to this model as anomalies during its inference. To enable the QHDNN to perform satisfactorily in deep image AD, we explore multiple quantum layer architectures and design a VQC-based QHDNN solution. Extensive experiments were conducted on commonly used benchmarks to test the proposed QML solution, whose results demonstrate the feasibility of addressing deep image AD with QML. Importantly, the experimental results show that our quantum-classical hybrid solution can even yield superior performance to that of its classical counterpart when they share the same number of learnable parameters. [ABSTRACT FROM AUTHOR]

The intelligent monitoring of tool wear status and wear prediction are important factors affecting the intelligent development of the modern machinery industry. Many scholars have used deep learning methods to achieve certain results in tool wear prediction. However, due to the instability and variability of the signal data, some neural network models may have gradient decay between layers. Most methods mainly focus on feature selection of the input data but ignore the influence degree of different features to tool wear. In order to solve these problems, this paper proposes a dual-stage attention model for tool wear prediction. A CNN-BiGRU-attention network model is designed, which introduces the self-attention to extract deep features and embody more important features. The IndyLSTM is used to construct a stable network to solve the gradient decay problem between layers. Moreover, the attention mechanism is added to the network to obtain the important information of output sequence, which can improve the accuracy of the prediction. Experimental study is carried out for tool wear prediction in a dry milling operation to demonstrate the viability of this method. Through the experimental comparison and analysis with regression prediction evaluation indexes, it proves the proposed method can effectively characterize the degree of tool wear, reduce the prediction errors, and achieve good prediction results. [ABSTRACT FROM AUTHOR]

In this work, we formulate the image in-painting as a matrix completion problem. Traditional matrix completion methods are generally based on linear models, assuming that the matrix is low rank. When the original matrix is large scale and the observed elements are few, they will easily lead to over-fitting and their performance will also decrease significantly. Recently, researchers have tried to apply deep learning and nonlinear techniques to solve matrix completion. However, most of the existing deep learning-based methods restore each column or row of the matrix independently, which loses the global structure information of the matrix and therefore does not achieve the expected results in the image in-painting. In this paper, we propose a deep matrix factorization completion network (DMFCNet) for image in-painting by combining deep learning and a traditional matrix completion model. The main idea of DMFCNet is to map iterative updates of variables from a traditional matrix completion model into a fixed depth neural network. The potential relationships between observed matrix data are learned in a trainable end-to-end manner, which leads to a high-performance and easy-to-deploy nonlinear solution. Experimental results show that DMFCNet can provide higher matrix completion accuracy than the state-of-the-art matrix completion methods in a shorter running time. [ABSTRACT FROM AUTHOR]

We feature papers on recent developments in the areas of adaptive signal processing, machine learning, and deep learning using information theory and entropy to improve performance in widespread and popular problems, and also to provide effective solutions to emerging problems. Our goal is to publish recent developments in the areas of adaptive signal processing, machine learning, and deep learning using information theory and entropy to improve performance in widespread and popular problems, and also to provide effective solutions to emerging problems. This Special Issue on "Adaptive Signal Processing and Machine Learning Using Entropy and Information Theory" was birthed from observations of the recent trend in the literature. Entropy-based cost functions have replaced mean-square-error (MSE)-based ones and have been widely used in adaptive signal processing and machine learning to improve performance by designing and optimizing effective and specific models that fit the data, even in noisy and adverse conditions. [Extracted from the article]

In this paper, we study the learnability of the Boolean inner product by a systematic simulation study. The family of the Boolean inner product function is known to be representable by neural networks of threshold neurons of depth 3 with only 2 n + 1 units (n the input dimension)—whereas an exact representation by a depth 2 network cannot possibly be of polynomial size. This result can be seen as a strong argument for deep neural network architectures. In our study, we found that this depth 3 architecture of the Boolean inner product is difficult to train, much harder than the depth 2 network, at least for the small input size scenarios n ≤ 16 . Nonetheless, the accuracy of the deep architecture increased with the dimension of the input space to 94% on average, which means that multiple restarts are needed to find the compact depth 3 architecture. Replacing the fully connected first layer by a partially connected layer (a kind of convolutional layer sparsely connected with weight sharing) can significantly improve the learning performance up to 99% accuracy in simulations. Another way to improve the learnability of the compact depth 3 representation of the inner product could be achieved by adding just a few additional units into the first hidden layer. [ABSTRACT FROM AUTHOR]

In this paper, a grid-free deep learning method based on a physics-informed neural network is proposed for solving coupled Stokes–Darcy equations with Bever–Joseph–Saffman interface conditions. This method has the advantage of avoiding grid generation and can greatly reduce the amount of computation when solving complex problems. Although original physical neural network algorithms have been used to solve many differential equations, we find that the direct use of physical neural networks to solve coupled Stokes–Darcy equations does not provide accurate solutions in some cases, such as rigid terms due to small parameters and interface discontinuity problems. In order to improve the approximation ability of a physics-informed neural network, we propose a loss-function-weighted function strategy, a parallel network structure strategy, and a local adaptive activation function strategy. In addition, the physical information neural network with an added strategy provides inspiration for solving other more complicated problems of multi-physical field coupling. Finally, the effectiveness of the proposed strategy is verified by numerical experiments. [ABSTRACT FROM AUTHOR]

When computers started to become a dominant part of technology around the 1950s, fundamental questions about reliable designs and robustness were of great relevance. Their development gave rise to the exploration of new questions, such as what made brains reliable (since neurons can die) and how computers could get inspiration from neural systems. In parallel, the first artificial neural networks came to life. Since then, the comparative view between brains and computers has been developed in new, sometimes unexpected directions. With the rise of deep learning and the development of connectomics, an evolutionary look at how both hardware and neural complexity have evolved or designed is required. In this paper, we argue that important similarities have resulted both from convergent evolution (the inevitable outcome of architectural constraints) and inspiration of hardware and software principles guided by toy pictures of neurobiology. Moreover, dissimilarities and gaps originate from the lack of major innovations that have paved the way to biological computing (including brains) that are completely absent within the artificial domain. As it occurs within synthetic biocomputation, we can also ask whether alternative minds can emerge from A.I. designs. Here, we take an evolutionary view of the problem and discuss the remarkable convergences between living and artificial designs and what are the pre-conditions to achieve artificial intelligence. [ABSTRACT FROM AUTHOR]

The spiking neural network (SNN) is regarded as a promising candidate to deal with the great challenges presented by current machine learning techniques, including the high energy consumption induced by deep neural networks. However, there is still a great gap between SNNs and the online meta-learning performance of artificial neural networks. Importantly, existing spike-based online meta-learning models do not target the robust learning based on spatio-temporal dynamics and superior machine learning theory. In this invited article, we propose a novel spike-based framework with minimum error entropy, called MeMEE, using the entropy theory to establish the gradient-based online meta-learning scheme in a recurrent SNN architecture. We examine the performance based on various types of tasks, including autonomous navigation and the working memory test. The experimental results show that the proposed MeMEE model can effectively improve the accuracy and the robustness of the spike-based meta-learning performance. More importantly, the proposed MeMEE model emphasizes the application of the modern information theoretic learning approach on the state-of-the-art spike-based learning algorithms. Therefore, in this invited paper, we provide new perspectives for further integration of advanced information theory in machine learning to improve the learning performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic systems. [ABSTRACT FROM AUTHOR]

Malware allegedly developed by nation-states, also known as advanced persistent threats (APT), are becoming more common. The task of attributing an APT to a specific nation-state or classifying it to the correct APT family is challenging for several reasons. First, each nation-state has more than a single cyber unit that develops such malware, rendering traditional authorship attribution algorithms useless. Furthermore, the dataset of such available APTs is still extremely small. Finally, those APTs use state-of-the-art evasion techniques, making feature extraction challenging. In this paper, we use a deep neural network (DNN) as a classifier for nation-state APT attribution. We record the dynamic behavior of the APT when run in a sandbox and use it as raw input for the neural network, allowing the DNN to learn high level feature abstractions of the APTs itself. We also use the same raw features for APT family classification. Finally, we use the feature abstractions learned by the APT family classifier to solve the attribution problem. Using a test set of 1000 Chinese and Russian developed APTs, we achieved an accuracy rate of 98.6% [ABSTRACT FROM AUTHOR]

Vector of locally aggregated descriptor (VLAD) coding has become an efficient feature coding model for retrieval and classification. In some recent works, the VLAD coding method is extended to a deep feature coding model which is called NetVLAD. NetVLAD improves significantly over the original VLAD method. Although the NetVLAD model has shown its potential for retrieval and classification, the discriminative ability is not fully researched. In this paper, we propose a new end-to-end feature coding network which is more discriminative than the NetVLAD model. First, we propose a sparsely-adaptive and covariance VLAD model. Next, we derive the back propagation models of all the proposed layers and extend the proposed feature coding model to an end-to-end neural network. Finally, we construct a multi-path feature coding network which aggregates multiple newly-designed feature coding networks for visual classification. Some experimental results show that our feature coding network is very effective for visual classification. [ABSTRACT FROM AUTHOR]

The use of a deep neural network scheme is proposed to help clinicians solve a difficult diagnosis problem in neurology. The proposed multilayer architecture includes a feature engineering step (from time-frequency transformation), a double compressing stage trained by unsupervised learning, and a classification stage trained by supervised learning. After fine-tuning, the deep network is able to discriminate well the class of patients from controls with around 90% sensitivity and specificity. This deep model gives better classification performance than some other standard discriminative learning algorithms. As in clinical problems there is a need for explaining decisions, an effort has been carried out to qualitatively justify the classification results. The main novelty of this paper is indeed to give an entropic interpretation of how the deep scheme works and reach the final decision. [ABSTRACT FROM AUTHOR]

Face verification for unrestricted faces in the wild is a challenging task. This paper proposes a method based on two deep convolutional neural networks (CNN) for face verification. In this work, we explore using identification signals to supervise one CNN and the combination of semi-verification and identification to train the other one. In order to estimate semi-verification loss at a low computation cost, a circle, which is composed of all faces, is used for selecting face pairs from pairwise samples. In the process of face normalization, we propose using different landmarks of faces to solve the problems caused by poses. In addition, the final face representation is formed by the concatenating feature of each deep CNN after principal component analysis (PCA) reduction. Furthermore, each feature is a combination of multi-scale representations through making use of auxiliary classifiers. For the final verification, we only adopt the face representation of one region and one resolution of a face jointing Joint Bayesian classifier. Experiments show that our method can extract effective face representation with a small training dataset and our algorithm achieves 99.71% verification accuracy on Labeled Faces in theWild (LFW) dataset. [ABSTRACT FROM AUTHOR]

The prediction of stock groups values has always been attractive and challenging for shareholders due to its inherent dynamics, non-linearity, and complex nature. This paper concentrates on the future prediction of stock market groups. Four groups named diversified financials, petroleum, non-metallic minerals, and basic metals from Tehran stock exchange were chosen for experimental evaluations. Data were collected for the groups based on 10 years of historical records. The value predictions are created for 1, 2, 5, 10, 15, 20, and 30 days in advance. Various machine learning algorithms were utilized for prediction of future values of stock market groups. We employed decision tree, bagging, random forest, adaptive boosting (Adaboost), gradient boosting, and eXtreme gradient boosting (XGBoost), and artificial neural networks (ANN), recurrent neural network (RNN) and long short-term memory (LSTM). Ten technical indicators were selected as the inputs into each of the prediction models. Finally, the results of the predictions were presented for each technique based on four metrics. Among all algorithms used in this paper, LSTM shows more accurate results with the highest model fitting ability. In addition, for tree-based models, there is often an intense competition between Adaboost, Gradient Boosting, and XGBoost. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) and Artificial Intelligence (AI) tools have shown great success in different areas of medical diagnostics. In this paper, we show another success in orthodontics. In orthodontics, the right treatment timing of many actions and operations is crucial because many environmental and genetic conditions may modify jaw growth. The stage of growth is related to the Cervical Vertebra Maturation (CVM) degree. Thus, determining the CVM to determine the suitable timing of the treatment is important. In orthodontics, lateral X-ray radiography is used to determine it. Many classical methods need knowledge and time to look and identify some features. Nowadays, ML and AI tools are used for many medical and biological diagnostic imaging. This paper reports on the development of a Deep Learning (DL) Convolutional Neural Network (CNN) method to determine (directly from images) the degree of maturation of CVM classified in six degrees. The results show the performances of the proposed method in different contexts with different number of images for training, evaluation and testing and different pre-processing of these images. The proposed model and method are validated by cross validation. The implemented software is almost ready for use by orthodontists. [ABSTRACT FROM AUTHOR]

In this paper, the performance of artificial neural networks in option pricing was analyzed and compared with the results obtained from the Black–Scholes–Merton model, based on the historical volatility. The results were compared based on various error metrics calculated separately between three moneyness ratios. The market data-driven approach was taken to train and test the neural network on the real-world options data from 2009 to 2019, quoted on the Warsaw Stock Exchange. The artificial neural network did not provide more accurate option prices, even though its hyperparameters were properly tuned. The Black–Scholes–Merton model turned out to be more precise and robust to various market conditions. In addition, the bias of the forecasts obtained from the neural network differed significantly between moneyness states. This study provides an initial insight into the application of deep learning methods to pricing options in emerging markets with low liquidity and high volatility. [ABSTRACT FROM AUTHOR]

Modeling and analysis of time series are important in applications including economics, engineering, environmental science and social science. Selecting the best time series model with accurate parameters in forecasting is a challenging objective for scientists and academic researchers. Hybrid models combining neural networks and traditional Autoregressive Moving Average (ARMA) models are being used to improve the accuracy of modeling and forecasting time series. Most of the existing time series models are selected by information-theoretic approaches, such as AIC, BIC, and HQ. This paper revisits a model selection technique based on Minimum Message Length (MML) and investigates its use in hybrid time series analysis. MML is a Bayesian information-theoretic approach and has been used in selecting the best ARMA model. We utilize the long short-term memory (LSTM) approach to construct a hybrid ARMA-LSTM model and show that MML performs better than AIC, BIC, and HQ in selecting the model—both in the traditional ARMA models (without LSTM) and with hybrid ARMA-LSTM models. These results held on simulated data and both real-world datasets that we considered.We also develop a simple MML ARIMA model. [ABSTRACT FROM AUTHOR]

Artificial neural networks have become the go-to solution for computer vision tasks, including problems of the security domain. One such example comes in the form of reidentification, where deep learning can be part of the surveillance pipeline. The use case necessitates considering an adversarial setting—and neural networks have been shown to be vulnerable to a range of attacks. In this paper, the preprocessing defences against adversarial attacks are evaluated, including block-matching convolutional neural network for image denoising used as an adversarial defence. The benefit of using preprocessing defences comes from the fact that it does not require the effort of retraining the classifier, which, in computer vision problems, is a computationally heavy task. The defences are tested in a real-life-like scenario of using a pre-trained, widely available neural network architecture adapted to a specific task with the use of transfer learning. Multiple preprocessing pipelines are tested and the results are promising. [ABSTRACT FROM AUTHOR]

Person re-identification in the image processing domain has been a challenging research topic due to the influence of pedestrian posture, background, lighting, and other factors. In this paper, the method of harsh learning is applied in person re-identification, and we propose a person re-identification method based on deep hash learning. By improving the conventional method, the method proposed in this paper uses an easy-to-optimize shallow convolutional neural network to learn the inherent implicit relationship of the image and then extracts the deep features of the image. Then, a hash layer with three-step calculation is incorporated in the fully connected layer of the network. The hash function is learned and mapped into a hash code through the connection between the network layers. The generation of the hash code satisfies the requirements that minimize the error of the sum of quantization loss and Softmax regression cross-entropy loss, which achieve the end-to-end generation of hash code in the network. After obtaining the hash code through the network, the distance between the pedestrian image hash code to be retrieved and the pedestrian image hash code library is calculated to implement the person re-identification. Experiments conducted on multiple standard datasets show that our deep hashing network achieves the comparable performances and outperforms other hashing methods with large margins on Rank-1 and mAP value identification rates in pedestrian re-identification. Besides, our method is predominant in the efficiency of training and retrieval in contrast to other pedestrian re-identification algorithms. [ABSTRACT FROM AUTHOR]

Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has been constrained to very restricted model classes, where exact or approximate probabilistic inference is feasible. However, developments in variational inference, a general form of approximate probabilistic inference that originated in statistical physics, have enabled probabilistic modeling to overcome these limitations: (i) Approximate probabilistic inference is now possible over a broad class of probabilistic models containing a large number of parameters, and (ii) scalable inference methods based on stochastic gradient descent and distributed computing engines allow probabilistic modeling to be applied to massive data sets. One important practical consequence of these advances is the possibility to include deep neural networks within probabilistic models, thereby capturing complex non-linear stochastic relationships between the random variables. These advances, in conjunction with the release of novel probabilistic modeling toolboxes, have greatly expanded the scope of applications of probabilistic models, and allowed the models to take advantage of the recent strides made by the deep learning community. In this paper, we provide an overview of the main concepts, methods, and tools needed to use deep neural networks within a probabilistic modeling framework. [ABSTRACT FROM AUTHOR]

Target tracking technology that is based on aerial videos is widely used in many fields; however, this technology has challenges, such as image jitter, target blur, high data dimensionality, and large changes in the target scale. In this paper, the research status of aerial video tracking and the characteristics, background complexity and tracking diversity of aerial video targets are summarized. Based on the findings, the key technologies that are related to tracking are elaborated according to the target type, number of targets and applicable scene system. The tracking algorithms are classified according to the type of target, and the target tracking algorithms that are based on deep learning are classified according to the network structure. Commonly used aerial photography datasets are described, and the accuracies of commonly used target tracking methods are evaluated in an aerial photography dataset, namely, UAV123, and a long-video dataset, namely, UAV20L. Potential problems are discussed, and possible future research directions and corresponding development trends in this field are analyzed and summarized. [ABSTRACT FROM AUTHOR]

Convolutional neural networks have powerful performances in many visual tasks because of their hierarchical structures and powerful feature extraction capabilities. SPD (symmetric positive definition) matrix is paid attention to in visual classification, because it has excellent ability to learn proper statistical representation and distinguish samples with different information. In this paper, a deep neural network signal detection method based on spectral convolution features is proposed. In this method, local features extracted from convolutional neural network are used to construct the SPD matrix, and a deep learning algorithm for the SPD matrix is used to detect target signals. Feature maps extracted by two kinds of convolutional neural network models are applied in this study. Based on this method, signal detection has become a binary classification problem of signals in samples. In order to prove the availability and superiority of this method, simulated and semi-physical simulated data sets are used. The results show that, under low SCR (signal-to-clutter ratio), compared with the spectral signal detection method based on the deep neural network, this method can obtain a gain of 0.5–2 dB on simulated data sets and semi-physical simulated data sets. [ABSTRACT FROM AUTHOR]

Automatic coal-rock recognition is one of the critical technologies for intelligent coal mining and processing. Most existing coal-rock recognition methods have some defects, such as unsatisfactory performance and low robustness. To solve these problems, and taking distinctive visual features of coal and rock into consideration, the multi-scale feature fusion coal-rock recognition (MFFCRR) model based on a multi-scale Completed Local Binary Pattern (CLBP) and a Convolution Neural Network (CNN) is proposed in this paper. Firstly, the multi-scale CLBP features are extracted from coal-rock image samples in the Texture Feature Extraction (TFE) sub-model, which represents texture information of the coal-rock image. Secondly, the high-level deep features are extracted from coal-rock image samples in the Deep Feature Extraction (DFE) sub-model, which represents macroscopic information of the coal-rock image. The texture information and macroscopic information are acquired based on information theory. Thirdly, the multi-scale feature vector is generated by fusing the multi-scale CLBP feature vector and deep feature vector. Finally, multi-scale feature vectors are input to the nearest neighbor classifier with the chi-square distance to realize coal-rock recognition. Experimental results show the coal-rock image recognition accuracy of the proposed MFFCRR model reaches 97.9167%, which increased by 2%–3% compared with state-of-the-art coal-rock recognition methods. [ABSTRACT FROM AUTHOR]

Face recognition is a popular and efficient form of biometric authentication used in many software applications. One drawback of this technique is that it is prone to face spoofing attacks, where an impostor can gain access to the system by presenting a photograph of a valid user to the sensor. Thus, face liveness detection is a necessary step before granting authentication to the user. In this paper, we have developed deep architectures for face liveness detection that use a combination of texture analysis and a convolutional neural network (CNN) to classify the captured image as real or fake. Our development greatly improved upon a recent approach that applies nonlinear diffusion based on an additive operator splitting scheme and a tridiagonal matrix block-solver algorithm to the image, which enhances the edges and surface texture in the real image. We then fed the diffused image to a deep CNN to identify the complex and deep features for classification. We obtained 100% accuracy on the NUAA Photograph Impostor dataset for face liveness detection using one of our enhanced architectures. Further, we gained insight into the enhancement of the face liveness detection architecture by evaluating three different deep architectures, which included deep CNN, residual network, and the inception network version 4. We evaluated the performance of each of these architectures on the NUAA dataset and present here the experimental results showing under what conditions an architecture would be better suited for face liveness detection. While the residual network gave us competitive results, the inception network version 4 produced the optimal accuracy of 100% in liveness detection (with nonlinear anisotropic diffused images with a smoothness parameter of 15). Our approach outperformed all current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Detecting and classifying ships based on radiated noise provide practical guidelines for the reduction of underwater noise footprint of shipping. In this paper, the detection and classification are implemented by auditory inspired convolutional neural networks trained from raw underwater acoustic signal. The proposed model includes three parts. The first part is performed by a multi-scale 1D time convolutional layer initialized by auditory filter banks. Signals are decomposed into frequency components by convolution operation. In the second part, the decomposed signals are converted into frequency domain by permute layer and energy pooling layer to form frequency distribution in auditory cortex. Then, 2D frequency convolutional layers are applied to discover spectro-temporal patterns, as well as preserve locality and reduce spectral variations in ship noise. In the third part, the whole model is optimized with an objective function of classification to obtain appropriate auditory filters and feature representations that are correlative with ship categories. The optimization reflects the plasticity of auditory system. Experiments on five ship types and background noise show that the proposed approach achieved an overall classification accuracy of 79.2%, which improved by 6% compared to conventional approaches. Auditory filter banks were adaptive in shape to improve accuracy of classification. [ABSTRACT FROM AUTHOR]

In this paper, a deep learning approach, Restricted Boltzmann Machine (RBM), is used to perform automatic hand sign language recognition from visual data. We evaluate how RBM, as a deep generative model, is capable of generating the distribution of the input data for an enhanced recognition of unseen data. Two modalities, RGB and Depth, are considered in the model input in three forms: original image, cropped image, and noisy cropped image. Five crops of the input image are used and the hand of these cropped images are detected using Convolutional Neural Network (CNN). After that, three types of the detected hand images are generated for each modality and input to RBMs. The outputs of the RBMs for two modalities are fused in another RBM in order to recognize the output sign label of the input image. The proposed multi-modal model is trained on all and part of the American alphabet and digits of four publicly available datasets. We also evaluate the robustness of the proposal against noise. Experimental results show that the proposed multi-modal model, using crops and the RBM fusing methodology, achieves state-of-the-art results on Massey University Gesture Dataset 2012, American Sign Language (ASL). and Fingerspelling Dataset from the University of Surrey's Center for Vision, Speech and Signal Processing, NYU, and ASL Fingerspelling A datasets. [ABSTRACT FROM AUTHOR]

Automatic question answering (QA), which can greatly facilitate the access to information, is an important task in artificial intelligence. Recent years have witnessed the development of QA methods based on deep learning. However, a great amount of data is needed to train deep neural networks, and it is laborious to annotate training data for factoid QA of new domains or languages. In this paper, a distantly supervised method is proposed to automatically generate QA pairs. Additional efforts are paid to let the generated questions reflect the query interests and expression styles of users by exploring the community QA. Specifically, the generated questions are selected according to the estimated probabilities they are asked. Diverse paraphrases of questions are mined from community QA data, considering that the model trained on monotonous synthetic questions is very sensitive to variants of question expressions. Experimental results show that the model solely trained on generated data via the distant supervision and mined paraphrases could answer real-world questions with the accuracy of 49.34%. When limited annotated training data is available, significant improvements could be achieved by incorporating the generated data. An improvement of 1.35 absolute points is still observed on WebQA, a dataset with large-scale annotated training samples. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (ConvNets), which are at the heart of many new emerging applications, achieve remarkable performance in audio and visual recognition tasks. Unfortunately, achieving accuracy often implies significant computational costs, limiting deployability. In modern ConvNets it is typical for the convolution layers to consume the vast majority of computational resources during inference. This has made the acceleration of these layers an important research area in academia and industry. In this paper, we examine the effects of co-optimizing the internal structures of the convolutional layers and underlying implementation of fundamental convolution operation. We demonstrate that a combination of these methods can have a big impact on the overall speedup of a ConvNet, achieving a ten-fold increase over baseline. We also introduce a new class of fast one-dimensional (1D) convolutions for ConvNets using the Toom–Cook algorithm. We show that our proposed scheme is mathematically well-grounded, robust, and does not require any time-consuming retraining, while still achieving speedups solely from convolutional layers with no loss in baseline accuracy. [ABSTRACT FROM AUTHOR]