Please use this identifier to cite or link to this item:
Title: Incremental neural network training with an increasing input dimension
Authors: Guan, S.-U. 
Liu, J.
Keywords: Feedforward network
Incremental training
Input attributes
Input dimension
Neural networks
Supervised learning
Issue Date: 2004
Source: Guan, S.-U.,Liu, J. (2004). Incremental neural network training with an increasing input dimension. Journal of Intelligent Systems 13 (1) : 45-69. ScholarBank@NUS Repository.
Abstract: Conventional Neural Network (NN) training is done by introducing training patterns in the full input dimension under batch mode. In this paper, an incremental training method with an increasing input dimension (ITID) is presented. ITID works by dividing the whole input dimension into several sub dimensions each of which corresponds to an input attribute. Instead of learning input attributes altogether as an input vector in a training instance, NN learns input attributes one after another through their corresponding sub-networks and the NN structure is grown incrementally with an increasing input dimension. During training, information obtained from a new sub-network is merged together with the information obtained from the old ones to refine the current NN structure. With less internal interference among input attributes, ITID achieves higher generalization accuracy than the conventional method. The experiment results of several benchmark problems show that ITID is efficient and effective for both classification and regression problems.
Source Title: Journal of Intelligent Systems
ISSN: 03341860
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

checked on Dec 15, 2017

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.