Staged training of Neocognitron by evolutionary algorithms

The Neocognitron, inspired by the mammalian visual system, is a complex neural network with numerous parameters and weights which should be trained in order to utilise it for pattern recognition. However, it is not easy to optimise these parameters and weights by gradient decent algorithms. We present a staged training approach using evolutionary algorithms. The experiments demonstrate that evolutionary algorithms can successfully train the Neocognitron to perform image recognition on real world problems.

[1]  R DyerCharles,et al.  Model-based recognition in robot vision , 1986 .

[2]  T Sabisch.  Towards automatic registration of magnetic resonance images of the brain using neural networks. , 1998 .

[3]  K Fukushima,et al.  Handwritten alphanumeric character recognition by the neocognitron , 1991, IEEE Trans. Neural Networks.

[4]  Kunihiko Fukushima,et al.  Neocognitron: A hierarchical neural network capable of visual pattern recognition , 1988, Neural Networks.

[5]  Geoffrey E. Hinton.  Learning Translation Invariant Recognition in Massively Parallel Networks , 1987, PARLE.

[6]  Malayappan Shridhar,et al.  High accuracy character recognition algorithm using fourier and topological descriptors , 1984, Pattern Recognit..

[7]  Ah Chung Tsoi,et al.  An evaluation of the neocognitron , 1997, IEEE Trans. Neural Networks.

[8]  Kunihiko Fukushima,et al.  Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..

[9]  Hamid Bolouri,et al.  Rotation, Translation, and Scaling Tolerant Recognition of Complex Shapes Using a Hierarchical Self-Organising Neural Network , 1997, ICONIP.

[10]  C.-H. Sung,et al.  Percognitron: Neocognitron coupled with perceptron , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[11]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[12]  Hamid Bolouri,et al.  Identification of complex shapes using a self organizing neural system , 2000, IEEE Trans. Neural Networks Learn. Syst..

[13]  A. Abutaleb,et al.  Automated analysis for scintigraphic evaluation of gastric emptying using invariant moments. , 1989, IEEE transactions on medical imaging.

[14]  Charles R. Dyer,et al.  Model-based recognition in robot vision , 1986, CSUR.

[15]  David Lovell,et al.  The neocognitron as a system for handwritten character recognition : limitations and improvements , 1994 .