Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 10 de 10
Filtrar
Mais filtros












Base de dados
Intervalo de ano de publicação
1.
Neural Netw ; 144: 496-506, 2021 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-34601362

RESUMO

Spiking neural networks (SNNs) aim to replicate energy efficiency, learning speed and temporal processing of biological brains. However, accuracy and learning speed of such networks is still behind reinforcement learning (RL) models based on traditional neural models. This work combines a pre-trained binary convolutional neural network with an SNN trained online through reward-modulated STDP in order to leverage advantages of both models. The spiking network is an extension of its previous version, with improvements in architecture and dynamics to address a more challenging task. We focus on extensive experimental evaluation of the proposed model with optimized state-of-the-art baselines, namely proximal policy optimization (PPO) and deep Q network (DQN). The models are compared on a grid-world environment with high dimensional observations, consisting of RGB images with up to 256 × 256 pixels. The experimental results show that the proposed architecture can be a competitive alternative to deep reinforcement learning (DRL) in the evaluated environment and provide a foundation for more complex future applications of spiking networks.


Assuntos
Redes Neurais de Computação , Reforço Psicológico , Encéfalo/diagnóstico por imagem , Recompensa
2.
IEEE Trans Neural Netw Learn Syst ; 31(9): 3741-3746, 2020 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-31562110

RESUMO

The ability of artificial neural networks (ANNs) to adapt to input data and perform generalizations is intimately connected to the use of nonlinear activation and propagation functions. Quantum versions of ANN have been proposed to take advantage of the possible supremacy of quantum over classical computing. To date, all proposals faced the difficulty of implementing nonlinear activation functions since quantum operators are linear. This brief presents an architecture to simulate the computation of an arbitrary nonlinear function as a quantum circuit. This computation is performed on the phase of an adequately designed quantum state, and quantum phase estimation recovers the result, given a fixed precision, in a circuit with linear complexity in function of ANN input size.

3.
BMC Bioinformatics ; 9: 497, 2008 Nov 27.
Artigo em Inglês | MEDLINE | ID: mdl-19038021

RESUMO

BACKGROUND: The use of clustering methods for the discovery of cancer subtypes has drawn a great deal of attention in the scientific community. While bioinformaticians have proposed new clustering methods that take advantage of characteristics of the gene expression data, the medical community has a preference for using "classic" clustering methods. There have been no studies thus far performing a large-scale evaluation of different clustering methods in this context. RESULTS/CONCLUSION: We present the first large-scale analysis of seven different clustering methods and four proximity measures for the analysis of 35 cancer gene expression data sets. Our results reveal that the finite mixture of Gaussians, followed closely by k-means, exhibited the best performance in terms of recovering the true structure of the data sets. These methods also exhibited, on average, the smallest difference between the actual number of classes in the data sets and the best number of clusters as indicated by our validation criteria. Furthermore, hierarchical methods, which have been widely used by the medical community, exhibited a poorer recovery performance than that of the other methods evaluated. Moreover, as a stable basis for the assessment and comparison of different clustering methods for cancer gene expression data, this study provides a common group of data sets (benchmark data sets) to be shared among researchers and used for comparisons with new methods. The data sets analyzed in this study are available at http://algorithmics.molgen.mpg.de/Supplements/CompCancer/.


Assuntos
Biologia Computacional/métodos , Perfilação da Expressão Gênica , Neoplasias/diagnóstico , Algoritmos , Análise por Conglomerados , DNA Complementar/metabolismo , Regulação Neoplásica da Expressão Gênica , Genes Neoplásicos , Humanos , Modelos Biológicos , Modelos Estatísticos , Família Multigênica , Neoplasias/genética , Distribuição Normal , Análise de Sequência com Séries de Oligonucleotídeos , Reconhecimento Automatizado de Padrão/métodos
4.
Neural Netw ; 21(9): 1363-79, 2008 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-18378116

RESUMO

This paper introduces an approach called Clustering and Co-evolution to Construct Neural Network Ensembles (CONE). This approach creates neural network ensembles in an innovative way, by explicitly partitioning the input space through a clustering method. The clustering method allows a reduction in the number of nodes of the neural networks that compose the ensemble, thus reducing the execution time of the learning process. This is an important characteristic especially when evolutionary algorithms are used. The clustering method also ensures that different neural networks specialize in different regions of the input space, working in a divide-and-conquer way, to maintain and improve the accuracy. Besides, the clustering method facilitates the understanding of the system and makes a straightforward distributed implementation possible. The experiments performed with seven classification databases and three different co-evolutionary algorithms show that CONE considerably reduces the execution time without prejudicing (and even improving) the accuracy, even when a distributed implementation is not used.


Assuntos
Evolução Biológica , Análise por Conglomerados , Redes Neurais de Computação , Algoritmos , Inteligência Artificial , Bases de Dados Factuais , Genética/estatística & dados numéricos
5.
IEEE Trans Neural Netw ; 17(6): 1452-9, 2006 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-17131660

RESUMO

This paper introduces a methodology for neural network 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.


Assuntos
Algoritmos , Armazenamento e Recuperação da Informação/métodos , Redes Neurais de Computação , Reconhecimento Automatizado de Padrão/métodos , Processamento de Sinais Assistido por Computador
6.
IEEE Trans Neural Netw ; 16(4): 996-9, 2005 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-16121742

RESUMO

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.


Assuntos
Algoritmos , Modelos Estatísticos , Redes Neurais de Computação , Reconhecimento Automatizado de Padrão/métodos , Simulação por Computador
7.
Int J Neural Syst ; 15(1-2): 137-49, 2005.
Artigo em Inglês | MEDLINE | ID: mdl-15912591

RESUMO

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.


Assuntos
Órgãos Artificiais , Redes Neurais de Computação , Nariz , Reconhecimento Automatizado de Padrão/métodos , Olfato/fisiologia , Animais , Lógica Fuzzy , Humanos , Análise de Componente Principal
9.
Int J Neural Syst ; 13(2): 77-86, 2003 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-12923920

RESUMO

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.


Assuntos
Algoritmos , Inteligência Artificial , Simulação por Computador , Redes Neurais de Computação , Reconhecimento Psicológico , Cibernética , Retroalimentação , Generalização Psicológica , Humanos , Nariz , Odorantes , Distribuição Aleatória , Fatores de Tempo , Pesos e Medidas
10.
Int J Neural Syst ; 13(2): 111-8, 2003 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-12923924

RESUMO

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.


Assuntos
Tomada de Decisões , Redes Neurais de Computação , Neurônios , Afeto , Animais , Atenção , Comportamento , Encéfalo/citologia , Encéfalo/fisiologia , Simulação por Computador , Meio Ambiente , Humanos , Controle Interno-Externo , Modelos Neurológicos , Distribuição Aleatória , Enquadramento Psicológico , Descritores
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...