A Bayesian Approach to Attention Control and Concept Abstraction

Representing and modeling knowledge in the face of uncertainty has always been a challenge in artificial intelligence. Graphical models are an apt way of representing uncertainty, and hidden variables in this framework are a way of abstraction of the knowledge. It seems that hidden variables can represent concepts, which reveal the relation among the observed phenomena and capture their cause and effect relationship through structure learning. Our concern is mostly on concept learning of situated agents, which learn while living, and attend to important states to maximize their expected reward. Therefore, we present an algorithm for sequential learning of Bayesian networks with hidden variables. The proposed algorithm employs the recent advancements in learning hidden variable networks for the batch case, and utilizes a mixture of approaches that allows for sequential learning of parameters and structure of the network. The incremental nature of this algorithm facilitates gradual learning of an agent, through its lifetime, as data is gathered progressively. Furthermore inference is made possible, when facing a large corpus of data that cannot be handled as a whole.

[1]  David Maxwell Chickering,et al.  Efficient Approximations for the Marginal Likelihood of Bayesian Networks with Hidden Variables , 1997, Machine Learning.

[2]  Nir Friedman,et al.  The Bayesian Structural EM Algorithm , 1998, UAI.

[3]  W. J. Nowack.  Neurobiology of Neocortex , 1989, Neurology.

[4]  P. Spirtes,et al.  Causation, prediction, and search , 1993 .

[5]  John K. Tsotsos,et al.  Neurobiology of Attention , 2005 .

[6]  Lucas Paletta,et al.  Attention Architectures for Machine Vision and Mobile Robots , 2005 .

[7]  Naftali Tishby,et al.  Multivariate Information Bottleneck , 2001, Neural Computation.

[8]  Nir Friedman,et al.  Learning Bayesian Networks with Local Structure , 1996, UAI.

[9]  Wai Lam,et al.  LEARNING BAYESIAN BELIEF NETWORKS: AN APPROACH BASED ON THE MDL PRINCIPLE , 1994, Comput. Intell..

[10]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[11]  Nir Friedman,et al.  Sequential Update of Bayesian Network Structure , 1997, UAI.

[12]  Majid Nili Ahmadabadi,et al.  Biologically Inspired Framework for Learning and Abstract Representation of Attention Control , 2008, WAPCV.

[13]  Richard E. Neapolitan,et al.  Learning Bayesian networks , 2007, KDD '07.

[14]  Nir Friedman,et al.  Learning Hidden Variable Networks: The Information Bottleneck Approach , 2005, J. Mach. Learn. Res..

[15]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

[16]  Michael I. Jordan.  Learning in Graphical Models , 1999, NATO ASI Series.

[17]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.

[18]  Eric Horvitz,et al.  Models of attention in computing and communication , 2003, Commun. ACM.

[19]  Nir Friedman,et al.  Learning Belief Networks in the Presence of Missing Values and Hidden Variables , 1997, ICML.

[20]  Naftali Tishby,et al.  The information bottleneck method , 2000, ArXiv.