Ecological Neural Networks for Object Recognition and Generalization

Generalization is a critical capacity for organisms. Modeling the behavior of organisms with neural networks, some type of generalizations appear to be accessible to neural networks but other types do not. In this paper we present two simulations. In the first simulation we show that while neural networks can recognize where an object is located in the retina even if they have never experienced that object in that position ('where' generalization subtask), they have difficulty in recognizing the identity of a familiar object in a new position ('what' generalization subtask). In the second simulation we explore the hypothesis that organisms find another solution to the problem of recognizing objects in different positions on their retina: they move their eyes so that objects are always seen in the same position in the retina. This strategy emerges spontaneously in ecological neural networks that are allowed to move their 'eye' in order to bring different portions of the visible world in the central portion of their retina.

[1]  S. Sathiya Keerthi,et al.  Evaluation of simple performance measures for tuning SVM hyperparameters , 2003, Neurocomputing.

[2]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[3]  Kanako Watanabe,et al.  ICB database: the gyrB database for identification and classification of bacteria , 2001, Nucleic Acids Res..

[4]  Volker Roth,et al.  Nonlinear Discriminant Analysis Using Kernel Functions , 1999, NIPS.

[5]  G. Wagner,et al.  What does it take to evolve behaviorally complex organisms? , 2003, Bio Systems.

[6]  Bairoch,et al.  Construction of the gyrB Database for the Identification and Classification of Bacteria. , 1998, Genome informatics. Workshop on Genome Informatics.

[7]  S. Kosslyn,et al.  Why are What and Where Processed by Separate Cortical Visual Systems? A Computational Investigation , 1989, Journal of Cognitive Neuroscience.

[8]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[9]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[10]  Bernhard Schölkopf,et al.  A Kernel Approach for Learning from Almost Orthogonal Patterns , 2002, PKDD.

[11]  Kiyoshi Asai,et al.  Marginalized kernels for biological sequences , 2002, ISMB.

[12]  G. Kane.  Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .

[13]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[14]  J. Andrade-Cetto.  Object Recognition , 2003 .

[15]  H. Kasai,et al.  Phylogeny of the genus Pseudomonas: intrageneric structure reconstructed from the nucleotide sequences of gyrB and rpoD genes. , 2000, Microbiology.

[16]  Domenico Parisi,et al.  Evolving Modular Architectures for Neural Networks , 2000, NCPW.

[17]  Daniel Hanisch,et al.  Co-clustering of biological networks and gene expression data , 2002, ISMB.

[18]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[19]  M. Kanehisa,et al.  Graph-driven features extraction from microarray data , 2002, physics/0206055.

[20]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .