Generalization of Features in the Assembly Neural Networks
The purpose of the paper is an experimental study of the formation of class descriptions, taking place during learning, in assembly neural networks. the assembly neural network is artificially partitioned into several sub-networks according to the number of classes that the network has to recognize. the features extracted from input data are represented in neural column structures of the sub-networks. Hebbian neural assemblies are formed in the column structure of the sub-networks by weight adaptation. a specific class description is formed in each sub-network of the assembly neural network due to intersections between the neural assemblies. the process of formation of class descriptions in the sub-networks is interpreted as feature generalization. a set of special experiments is performed to study this process, on a task of character recognition using the MNIST database.
D. C. Wunsch and A. Goltsev, "Generalization of Features in the Assembly Neural Networks," International Journal of Neural Systems, World Scientific Publishing, Jan 2004.
Electrical and Computer Engineering
Keywords and Phrases
Neural Assembly; Neuron; Excitatory Binary Connection; Generation; Neural Column; Recognition; Sub-Network
Article - Journal
© 2004 World Scientific Publishing, All rights reserved.
This document is currently not available here.