.png){kind=icon}
.png){kind=icon}
Return
Feedforward neural network's sensitivity to input data representation
.png){kind=icon}
PRE
AI
DOI：10.1016/S0010-4655(98)00172-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Neural networks can be used to develop solutions to problems which are strictly symbolic. A question arises how to represent symbols in terms of number vectors understandable to neural networks. Data representation used should promote good generalization and reduce simulation uncertainty of the resulting model. Straightforward methods, which are most widely used, result in large networks which can prohibit solution of large problems. In the paper some new methods, which try to build information about the problem at hand into the representation, are proposed. It is shown that they are less sensitive to input data errors. (C) 1999 Elsevier Science B.V.
Keywords:
artificial neural networks
input data sensitivity
distributed data representation
simulation uncertainty
symbolic data manipulation
phonological transformation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.4
Papers:
1.2W
Citations:
3.7W
Organization
No organization information available