Coupling of Evolution and Learning to Optimize a Hierarchical Object Recognition Model

A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization methods can help to solve this problem. In this work we compare different evolutionary optimization approaches for a biologically inspired neural vision system: Direct coding versus a biologically more plausible indirect coding using unsupervised local learning. A comparison to state-of-the-art recognition approaches shows the competitiveness of our approach.

[1]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[2]  M.M. Van Hulle,et al.  View-based 3D object recognition with support vector machines , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[3]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[4]  Hiroshi Murase,et al.  Real-time 100 object recognition system , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[5]  Rod Adams,et al.  Towards Computational Neural Systems through Developmental Evolution , 2001, Emergent Neural Computational Architectures Based on Neuroscience.

[6]  Bernhard Sendhoff,et al.  A Model for the Dynamic Interaction Between Evolution and Learning , 2004, Neural Processing Letters.

[7]  Heiko Wersing,et al.  Learning Optimized Features for Hierarchical Models of Invariant Object Recognition , 2003, Neural Computation.

[8]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[9]  Heiko Wersing,et al.  Unsupervised Learning of Combination Features for Hierarchical Recognition Models , 2002, ICANN.

[10]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[11]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[12]  Günter Rudolph,et al.  Contemporary Evolution Strategies , 1995, ECAL.

[13]  E. Rolls,et al.  On the design of neural networks in the brain by genetic evolution , 2000, Progress in Neurobiology.

[14]  T. Sejnowski,et al.  Irresistible environment meets immovable neurons , 1997, Behavioral and Brain Sciences.

[15]  H. Barlow.  The Twelfth Bartlett Memorial Lecture: The Role of Single Neurons in the Psychology of Perception , 1985, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[16]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.