Faster Learning with Overlapping Neural Assemblies
Cell assemblies in neural network are often assumed as overlapping, i.e. a neuron may belong to several of them simultaneously. We argue that network structures with overlapping cell assemblies can exhibit faster learning comparing to non-overlapping ones. In such structures newly trained assemblies take advantage of their overlaps with the already trained neighbors. The assemblies learned in such manner nevertheless preserve the ability for subsequent separate firing. We discuss the implications it may have for intensification of neural network training methods and we also propose to view this learning speed-up in a broader context of inter-assembly cooperation useful for modeling concept formation in human thinking.
KeywordsInput Pattern Excitatory Neuron Faster Learn Connection Matrix Input Link
Unable to display preview. Download preview PDF.
- 1.Hebb, D.O.: The Organization of Behavior. A Neuropsychological Theory. John Wiley, New York (1949)Google Scholar
- 2.Palm, G.: Neural Assemblies. Studies of Brain Function, vol. VII. Springer, Heidelberg (1982)Google Scholar
- 3.Wickelgren, W.A.: Webs, Cell Assemblies, and Chunking in Neural Nets. Canadian Journal of Experimental psychology 53(1), 118–131 (1999)Google Scholar
- 10.Kursin, A.: Self-Organization of Anticipatory Neural Network. Scientific Proceedings Of Riga Technical University, Riga. series Computer Science, Information Technology and Management Science, pp. 51–59 (2004)Google Scholar
- 11.Lakoff, G., Johnson, M.: Metaphors We Live By. Univ. of Chicago Press, Chicago (1980)Google Scholar