Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/30762
Title: Sensitivity analysis of prior knowledge in knowledge-based neurocomputing
Authors: Cloete, I
Snyder, S
Yeung, DS
Wang, X
Keywords: Encoding
Knowledge based systems
Learning (artificial intelligence)
Neural nets
Sensitivity analysis
Issue Date: 2004
Publisher: IEEE
Source: Proceedings of 2004 International Conference on Machine Learning and Cybernetics, 2004, 26-29 August 2004, v. 7, p. 4174-4180 How to cite?
Abstract: Knowledge-based neurocomputing addresses, among other things, the encoding and refinement of symbolic knowledge in a neurocomputing paradigm. Prior symbolic knowledge derived outside of neural networks can be encoded in neural network form, and then further trained. Previous research suggested certain values for the weights that represent prior knowledge, based on an analysis of the derivative of the error function. This inductive bias is investigated empirically, and furthermore, we show how to use sensitivity analysis methods to investigate this bias. This work shows that the bias of the encoding method for the prior knowledge corresponds well with a range of good parameter values that retain the encoded knowledge and allows refinement by further training.
URI: http://hdl.handle.net/10397/30762
ISBN: 0-7803-8403-2
DOI: 10.1109/ICMLC.2004.1384572
Appears in Collections:Conference Paper

SFX Query Show full item record

Page view(s)

39
Last Week
0
Last month
Citations as of Dec 11, 2017

Google ScholarTM

Check

Altmetric


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