Please use this identifier to cite or link to this item:
|Title:||Towards minimal network architectures with evolutionary growth networks||Authors:||Romaniuk, Steve G.||Issue Date:||1994||Citation:||Romaniuk, Steve G. (1994). Towards minimal network architectures with evolutionary growth networks. IEEE International Conference on Neural Networks - Conference Proceedings 3 : 1710-1712. ScholarBank@NUS Repository.||Abstract:||This paper points out how simple learning rules such as perceptron and delta can be re-introduced as local learning techniques to yield an effective automatic network construction algorithm. This feat is accomplished by chosing the right training set during network construction. The choice of partitions can have profound affects on the quality of the created networks, in terms of number of hidden units and connections. Selection of partitions during various network construction phases is achieved by means of evolutionary processes. Empirical evidence underlining the effectiveness of this approach is provided for several well known benchmark problems such as parity, encoder and adder functions.||Source Title:||IEEE International Conference on Neural Networks - Conference Proceedings||URI:||http://scholarbank.nus.edu.sg/handle/10635/134159|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.