Search

In this paper we propose a procedure to enable the training of several independent Multilayer Perceptron Neural Networks with a different number of neurons and activation functions in parallel (ParallelMLPs) by exploring the principle of locality and parallelization capabilities of modern CPUs and GPUs. The core idea of this technique is to represent several sub-networks as a single large network and use a Modified Matrix Multiplication that replaces an ordinal matrix multiplication with two simple matrix operations that allow separate and independent paths for gradient flowing. We have assessed our algorithm in simulated datasets varying the number of samples, features and batches using 10,000 different models as well as in the MNIST dataset. We achieved a training speedup from 1 to 4 orders of magnitude if compared to the sequential approach. The code is available online. [ABSTRACT FROM AUTHOR]

Highlights: [•] We present a method for optimization of the activation functions for ANN. [•] The proposed optimization method uses Simulated Annealing and Tabu Search. [•] The proposed method is good for forecasting distinct time series. [ABSTRACT FROM AUTHOR]

Abstract: Social class differences in the prevalence of Common Mental Disorder (CMD) are likely to vary according to time, culture and stage of economic development. The present study aimed to investigate the use of optimization of architecture and weights of Artificial Neural Network (ANN) for identification of the factors related to CMDs. The identification of the factors was possible by optimizing the architecture and weights of the network. The optimization of architecture and weights of ANNs is based on Particle Swarm Optimization with early stopping criteria. This approach achieved a good generalization control, as well as similar or better results than other techniques, but with a lower computational cost, with the ability to generate small networks and with the advantage of the automated architecture selection, which simplify the training process. This paper presents the results obtained in the experiments with ANNs in which it was observed an average percentage of correct classification of individuals with positive diagnostic for the CMDs of 90.59%. [Copyright &y& Elsevier]

Abstract: Reservoir computing is a framework for computation like a recurrent neural network that allows for the black box modeling of dynamical systems. In contrast to other recurrent neural network approaches, reservoir computing does not train the input and internal weights of the network, only the readout is trained. However it is necessary to adjust parameters to create a “good” reservoir for a given application. In this study we introduce a method, called RCDESIGN (reservoir computing and design training). RCDESIGN combines an evolutionary algorithm with reservoir computing and simultaneously looks for the best values of parameters, topology and weight matrices without rescaling the reservoir matrix by the spectral radius. The idea of adjust the spectral radius within the unit circle in the complex plane comes from the linear system theory. However, this argument does not necessarily apply to nonlinear systems, which is the case of reservoir computing. The results obtained with the proposed method are compared with results obtained by a genetic algorithm search for global parameters generation of reservoir computing. Four time series were used to validate RCDESIGN. [Copyright &y& Elsevier]

The performance of an artificial neural network (ANN) depends upon the selection of proper connection weights, network architecture, and cost function during network training. This paper presents a hybrid approach (GaTSa) to optimize the performance of the ANN in terms of architecture and weights. GaTSa is an extension of a previous method (TSa) proposed by the authors. GaTSa is based on the integration of the heuristic simulated annealing (SA), tabu search (TS), genetic algorithms (GA), and backpropagation, whereas TSa does not use GA. The main advantages of GaTSa are the following: a constructive process to add new nodes in the architecture based on GA, the ability to escape from local minima with uphill moves (SA feature), and faster convergence by the evaluation of a set of solutions (TS feature). The performance of GaTSa is investigated through an empirical evaluation of 11 public-domain data sets using different cost functions in the simultaneous optimization of the multilayer perceptron ANN architecture and weights. Experiments demonstrated that GaTSa can also be used for relevant feature selection. GaTSa presented statistically relevant results in comparison with other global and local optimization techniques. [ABSTRACT FROM PUBLISHER]

This paper introduces a methodology for neural net- work global optimization. The aim is the simultaneous optimization of multilayer perceptron (MLP) network weights and architectures, in order to generate topologies with few connections and high classification performance for any data sets. The approach combines the advantages of simulated annealing, tabu search and the backpropagation training algorithm in order to generate an automatic process for producing networks with high classification performance and low complexity. Experimental results obtained with four classification problems and one prediction problem has shown to be better than those obtained by the most commonly used optimization techniques. [ABSTRACT FROM AUTHOR]

In this letter, the computational power of a class of random access memory (RAM)-based neural networks, called general single-layer sequential weightless neural networks (GSSWNNs), is analyzed. The theoretical results presented, besides helping the understanding of the temporal behavior of these networks, could also provide useful insights for the developing of new learning algorithms. [ABSTRACT FROM AUTHOR]

This work examines the use of Hybrid Intelligent Systems in the pattern recognition system of an artificial nose. The connectionist approaches Multi-Layer Perceptron and Time Delay Neural Networks, and the hybrid approaches Feature-Weighted Detector and Evolving Neural Fuzzy Networks were investigated. A Wavelet Filter is evaluated as a preprocessing method for odor signals. The signals generated by an artificial nose were composed by an array of conducting polymer sensors and exposed to two different odor databases. [ABSTRACT FROM AUTHOR]

This paper presents an approach of using Simulated Annealing and Tabu Search for the simultaneous optimization of neural network architectures and weights. The problem considered is the odor recognition in an artificial nose. Both methods have produced networks with high classification performance and low complexity. Generalization has been improved by using the backpropagation algorithm for fine tuning. The combination of simple and traditional search methods has shown to be very suitable for generating compact and efficient networks. [ABSTRACT FROM AUTHOR]

Neuronal groups projecting widely in the brain are being experimentally associated to attention and mood changes. Those groups are known to exert a modulatory effect over other larger groups. On the other hand, some people think of the brain functions as being performed by specialized modular systems. In this work, we propose an architecture of modular nature to explore a particular decision process. We show the importance of the modulatory effect of a special evaluation segment in that process. [ABSTRACT FROM AUTHOR]

Cites several abstracts on neural systems submitted at the VIIth Brazilian Symposium on Artificial Neural Networks held in 2002 at Porto De Galinhas-Pernambuco. Ways on how to deal with non-orthogonal signals by Allan Kardex Barros, Andrzej Cichocki and Noboru Ohnishi; Neuro-symbolic language for monotonic and non-monotonic parallel logical inference by means of artificial neural networks; Performance of fuzzy combination schemes.

A large number of classification algorithms have been proposed in the machine learning literature. These algorithms have different pros and cons, and no algorithm is the best for all datasets. Hence, a challenging problem consists of choosing the best classification algorithm with its best hyper-parameter settings for a given input dataset. In the last few years, Automated Machine Learning (Auto-ML) has emerged as a promising approach for tackling this problem, by doing a heuristic search in a large space of candidate classification algorithms and their hyper-parameter settings. In this work we propose an improved version of our previous Evolutionary Algorithm (EA) – more precisely, an Estimation of Distribution Algorithm – for the Auto-ML task of automatically selecting the best classifier ensemble and its best hyper-parameter settings for an input dataset. The new version of this EA was compared against its previous version, as well as against a random forest algorithm (a strong ensemble algorithm) and a version of the well-known Auto-ML method Auto-WEKA adapted to search in the same space of classifier ensembles as the proposed EA. In general, in experiments with 21 datasets, the new EA version obtained the best results among all methods in terms of four popular predictive accuracy measures: error rate, precision, recall and F-measure. [ABSTRACT FROM AUTHOR]

Interest in hybrid methods that combine artificial neural networks and fuzzy inference systems has grown in recent years. These systems are robust solutions that search for representations of domain knowledge, reasoning on uncertainty, automatic learning and adaptation. However, the design and definition of the parameter effectiveness of such systems is still a hard task. In the present work, we perform a statistical analysis to verify interactions and interrelations between parameters in the design of neuro-fuzzy systems. The analysis is carried out using a powerful statistical tool, namely, Design of Experiments (DOE), in two neuro-fuzzy models — Adaptive Neuro Fuzzy Inference System (ANFIS) and Evolving Fuzzy Neural Networks (EFuNN). The results show that, for ANFIS, input MFs number and output MFs shape are usually the factors with the largest influence on the system's RMSE. For EFFuNN, the MF shape and the interaction between MF shape and number usually have the largest effect size. [ABSTRACT FROM AUTHOR]

A fundamental question in the field of artificial neural networks is what set of problems a given class of networks can perform (computability). Such a problem can be made less general, but no less important, by asking what these networks could learn by using a given training procedure (learnability). The basic purpose of this paper is to address the learnability problem. Specifically, it analyses the learnability of sequential RAM-based neural networks. The analytical tools used are those of Automata Theory. In this context, this paper establishes which class of problems and under what conditions such networks, together with their existing learning rules, can learn and generalise. This analysis also yields techniques for both extracting knowledge from and inserting knowledge into the networks. The results presented here, besides helping in a better understanding of the temporal behaviour of sequential RAM-based networks, could also provide useful insights for the integration of the symbolic/connectionist paradigms. [ABSTRACT FROM AUTHOR]

Millions of people throughout the world describe themselves as being deaf. Some of them suffer from severe hearing loss and consequently use an alternative manner with which to communicate with society by means of either written or visual language. There are several sign languages capable of dealing with such a need. Nonetheless, a communication gap still exists even when using such languages, since only a small fraction of the population is able to use them. Over the last few years, due to the increasing need for universal accessibility when using computational resources, gesture recognition has been widely researched. Thus, in an attempt to reduce this communication gap, our approach proposes a computational solution in order to translate static gesture symbols into text symbols, through computer vision, without the use of hand sensors or gloves. In order to guarantee the highest quality, with emphasis on the reliability of the system and real-time translation, we have developed an approach based on the Extreme Learning Machine (ELM) pattern recognition algorithms fully implemented in hardware, and have assessed it to measure these two metrics. Hardware components were designed in order to perform the best image processing and pattern recognition tasks used within the project. As a case study, and so as to validate the technique, a recognition system for the Brazilian Sign Language (LIBRAS) was implemented. Besides ensuring that this approach could be used for any static hand gesture symbol recognition, our main goal was to guarantee fast, reliable gesture recognition for communication between humans. Experimental results have demonstrated that the system is able to recognize LIBRAS symbols with an accuracy of 97%, a response time of 6.5ms per letter recognition, and using only 43% (about 64,851 logic elements) of the FPGA area. [ABSTRACT FROM AUTHOR]