Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 6 de 6
Mais filtros

Base de dados
Intervalo de ano de publicação
Neural Netw ; 23(8-9): 973-84, 2010.
Artigo em Inglês | MEDLINE | ID: mdl-20951334


The ability to detect social contingencies plays an important role in the social and emotional development of infants. Analyzing this problem from a computational perspective may provide important clues for understanding social development, as well as for the synthesis of social behavior in robots. In this paper, we show that the turn-taking behaviors observed in infants during contingency detection situations are tuned to optimally gather information as to whether a person is responsive to them. We show that simple reinforcement learning mechanisms can explain how infants acquire these efficient contingency detection schemas. The key is to use the reduction of uncertainty (information gain) as a reward signal. The result is an interesting form of learning in which the learner rewards itself for conducting actions that help reduce its own sense of uncertainty. This paper illustrates the possibilities of an emerging area of computer science and engineering that focuses on the computational understanding of human behavior and on its synthesis in robots. We believe that the theory of stochastic optimal control will play a key role providing a formal mathematical foundation for this newly emerging discipline.

Desenvolvimento Infantil/fisiologia , Comportamento Social , Meio Social , Algoritmos , Inteligência Artificial , Fenômenos Biomecânicos , Simulação por Computador , Retroalimentação Psicológica , Humanos , Lactente , Aprendizagem/fisiologia , Masculino , Modelos Psicológicos , Modelos Estatísticos , Recompensa , Robótica , Processos Estocásticos
IEEE Trans Pattern Anal Mach Intell ; 32(2): 348-63, 2010 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-20075463


We present a generative model and inference algorithm for 3D nonrigid object tracking. The model, which we call G-flow, enables the joint inference of 3D position, orientation, and nonrigid deformations, as well as object texture and background texture. Optimal inference under G-flow reduces to a conditionally Gaussian stochastic filtering problem. The optimal solution to this problem reveals a new space of computer vision algorithms, of which classic approaches such as optic flow and template matching are special cases that are optimal only under special circumstances. We evaluate G-flow on the problem of tracking facial expressions and head motion in 3D from single-camera video. Previously, the lack of realistic video data with ground truth nonrigid position information has hampered the rigorous evaluation of nonrigid tracking. We introduce a practical method of obtaining such ground truth data and present a new face video data set that was created using this technique. Results on this data set show that G-flow is much more robust and accurate than current deterministic optic-flow-based approaches.

Algoritmos , Face/anatomia & histologia , Processamento de Imagem Assistida por Computador/métodos , Movimento/fisiologia , Distribuição Normal , Reconhecimento Automatizado de Padrão/métodos , Humanos , Processos Estocásticos , Gravação em Vídeo
Neural Comput ; 20(9): 2238-52, 2008 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-18439142


This letter presents an analysis of the contrastive divergence (CD) learning algorithm when applied to continuous-time linear stochastic neural networks. For this case, powerful techniques exist that allow a detailed analysis of the behavior of CD. The analysis shows that CD converges to maximum likelihood solutions only when the network structure is such that it can match the first moments of the desired distribution. Otherwise, CD can converge to solutions arbitrarily different from the log-likelihood solutions, or they can even diverge. This result suggests the need to improve our theoretical understanding of the conditions under which CD is expected to be well behaved and the conditions under which it may fail. In, addition the results point to practical ideas on how to improve the performance of CD.

Aprendizagem/fisiologia , Redes Neurais de Computação , Distribuição Normal , Algoritmos , Humanos , Modelos Lineares
Proc Natl Acad Sci U S A ; 104(46): 17954-8, 2007 Nov 13.
Artigo em Inglês | MEDLINE | ID: mdl-17984068


A state-of-the-art social robot was immersed in a classroom of toddlers for >5 months. The quality of the interaction between children and robots improved steadily for 27 sessions, quickly deteriorated for 15 sessions when the robot was reprogrammed to behave in a predictable manner, and improved in the last three sessions when the robot displayed again its full behavioral repertoire. Initially, the children treated the robot very differently than the way they treated each other. By the last sessions, 5 months later, they treated the robot as a peer rather than as a toy. Results indicate that current robot technology is surprisingly close to achieving autonomous bonding and socialization with human toddlers for sustained periods of time and that it could have great potential in educational settings assisting teachers and enriching the classroom environment.

Relações Interpessoais , Robótica/instrumentação , Instituições Acadêmicas , Comportamento Social , Pré-Escolar , Feminino , Humanos , Lactente , Masculino
Neurocomputing ; 58-60: 893-900, 2004 Jun 01.
Artigo em Inglês | MEDLINE | ID: mdl-21113307


Neural models of contextual integration typically incorporate a mean firing rate representation. We examine representation of the full spike count distribution, and its usefulness in explaining contextual integration of color stimuli in primary visual cortex. Specifically, we demonstrate that a factorizable model conditioned on the number of spikes can account for both the onset and sustained portions of the response. We also consider a simplified factorizable model that parametrizes the mean of a Gaussian distribution and incorporates a logistic nonlinearity. The model can account for the sustained response but does not fair as well in accounting for onset nonlinearities. We discuss implications for neural coding.

Neural Comput ; 14(7): 1507-44, 2002 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-12079544


We present a Monte Carlo approach for training partially observable diffusion processes. We apply the approach to diffusion networks, a stochastic version of continuous recurrent neural networks. The approach is aimed at learning probability distributions of continuous paths, not just expected values. Interestingly, the relevant activation statistics used by the learning rule presented here are inner products in the Hilbert space of square integrable functions. These inner products can be computed using Hebbian operations and do not require backpropagation of error signals. Moreover, standard kernel methods could potentially be applied to compute such inner products. We propose that the main reason that recurrent neural networks have not worked well in engineering applications (e.g., speech recognition) is that they implicitly rely on a very simplistic likelihood model. The diffusion network approach proposed here is much richer and may open new avenues for applications of recurrent neural networks. We present some analysis and simulations to support this view. Very encouraging results were obtained on a visual speech recognition task in which neural networks outperformed hidden Markov models.

Inteligência Artificial , Método de Monte Carlo , Redes Neurais de Computação , Algoritmos , Difusão , Humanos , Leitura Labial , Reconhecimento Visual de Modelos , Fala , Processos Estocásticos