For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Hopfield Neural Network Learning Using Direct Gradient Descent of Energy Function
Zheng TANG Koichi TASHIMA Hirofumi HEBISHIMA Okihiko ISHIZUKA Koichi TANNO
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1996/02/25
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Neural Networks
neural networks, gradient descent learning, Hopfield model, analog-to-digital conversion, associative memory,
Full Text: PDF(247.7KB)>>
A direct gradient descent learning algorithm of energy function in Hopfield neural networks is proposed. The gradient descent learning is not performed on usual error functions, but the Hopfield energy functions directly. We demonstrate the algorithm by testing it on an analog-to-digital conversion and an associative memory problems.