DocumentCode :
768221
Title :
Programming based learning algorithms of neural networks with self-feedback connections
Author :
Zhang, Ling ; Ling Zhaog ; Wu, Fuchao
Author_Institution :
Dept. of Comput. Sci., Tsinghua Univ., Beijing, China
Volume :
6
Issue :
3
fYear :
1995
fDate :
5/1/1995 12:00:00 AM
Firstpage :
771
Lastpage :
775
Abstract :
Discusses the learning problem of neural networks with self-feedback connections and shows that when the neural network is used as associative memory, the learning problem can be transformed into some sort of programming (optimization) problem. Thus, the rather mature optimization technique in programming mathematics can be used for solving the learning problem of neural networks with self-feedback connections. Two learning algorithms based on programming technique are presented. Their complexity is just polynomial. Then, the optimization of the radius of attraction of the training samples is discussed using quadratic programming techniques and the corresponding algorithm is given. Finally, the comparison is made between the given learning algorithm and some other known algorithms
Keywords :
computational complexity; learning (artificial intelligence); neural nets; quadratic programming; associative memory; neural networks; optimization technique; programming based learning algorithms; quadratic programming; self-feedback connections; Associative memory; Computer science; Ellipsoids; Functional programming; Mathematical programming; Mathematics; Neural networks; Neurofeedback; Polynomials; Quadratic programming;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/72.377985
Filename :
377985
Link To Document :
بازگشت