DocumentCode :
3253016
Title :
A unified formalism for neural net training algorithms
Author :
Bottou, Léon ; Gallinari, Patrick
Author_Institution :
AT&T Bell Labs., Holmdel, NJ, USA
Volume :
4
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
7
Abstract :
The authors present a framework which provides both a unified formalism for describing many connectionist algorithms and a formal definition of the goal of learning for these algorithms. This formal approach is illustrated through several examples from among the classical connectionist literature. Many nonconnectionist systems also fall into this formulation which is thus very general and has several consequences on the design of connectionist systems. For example it allows the training of optimally hybrid architectures where different connectionist or classical modules interact
Keywords :
learning (artificial intelligence); neural nets; connectionist algorithms; neural net training algorithms; optimally hybrid architectures; unified formalism; Adaptive filters; Cost function; Learning systems; Mathematical analysis; Neural networks; Probability density function; Random processes; Stochastic processes; Supervised learning; Unsupervised learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227347
Filename :
227347
Link To Document :
بازگشت