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.
Asymmetric Neural Network and Its Application to Knapsack Problem
Akira YAMAMOTO Masaya OHTA Hiroshi UEDA Akio OGIHARA Kunio FUKUNAGA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1995/03/25
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section of Selected Papers from the 7th Karuizawa Workshop on Circuits and Systems)
Category: Neural Networks
neural network, asymmetric connection matrix, knapsack problem,
Full Text: PDF>>
We propose an asymmetric neural network which can solve inequality-constrained combinatorial optimization problems that are difficult to solve using symmetric neural networks. In this article, a knapsack problem that is one of such the problem is solved using the proposed network. Additionally, we study condition for obtaining a valid solution. In computer simulations, we show that the condition is correct and that the proposed network produces better solutions than the simple greedy algorithm.