DocumentCode :
749469
Title :
Binary neural systems: combining weighted and weightless properties
Author :
Aleksander, I. ; Clarke, T.J.W. ; Braga, A.P.
Author_Institution :
Dept. of Electr. & Electron. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
Volume :
3
Issue :
4
fYear :
1994
Firstpage :
211
Lastpage :
221
Abstract :
A neural function is developed that combines the characteristics of weightless and weighted binary neurons. A new combined generalisation algorithm is presented and applied to a neural state machine which is capable of learning to respond to sequences of inputs. The difficulty with such tasks lies in learning appropriate internal state assignments. A particular “iconic” method of solving this problem is discussed. The analysis includes a discussion of implementational issues
Keywords :
generalisation (artificial intelligence); neural nets; sequences; binary neural systems; generalisation algorithm; iconic method; implementational issues; neural state machine; weighted properties; weightless properties;
fLanguage :
English
Journal_Title :
Intelligent Systems Engineering
Publisher :
iet
ISSN :
0963-9640
Type :
jour
Filename :
370487
Link To Document :
بازگشت