|
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.
|
Avoidance of the Permanent Oscillating State in the Inverse Function Delayed Neural Network
Akari SATO Yoshihiro HAYAKAWA Koji NAKAJIMA
Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Vol.E90-A
No.10
pp.2101-2107 Publication Date: 2007/10/01 Online ISSN: 1745-1337
DOI: 10.1093/ietfec/e90-a.10.2101 Print ISSN: 0916-8508 Type of Manuscript: Special Section PAPER (Special Section on Nonlinear Theory and its Applications) Category: Neuron and Neural Networks Keyword: neural network, combinatorial optimization problem, N-Queen problem, inverse function delayed model, negative resistance,
Full Text: PDF(331.8KB)>>
Summary:
Many researchers have attempted to solve the combinatorial optimization problems, that are NP-hard or NP-complete problems, by using neural networks. Though the method used in a neural network has some advantages, the local minimum problem is not solved yet. It has been shown that the Inverse Function Delayed (ID) model, which is a neuron model with a negative resistance on its dynamics and can destabilize an intended region, can be used as the powerful tool to avoid the local minima. In our previous paper, we have shown that the ID network can separate local minimum states from global minimum states in case that the energy function of the embed problem is zero. It can achieve 100% success rate in the N-Queen problem with the certain parameter region. However, for a wider parameter region, the ID network cannot reach a global minimum state while all of local minimum states are unstable. In this paper, we show that the ID network falls into a particular permanent oscillating state in this situation. Several neurons in the network keep spiking in the particular permanent oscillating state, and hence the state transition never proceed for global minima. However, we can also clarify that the oscillating state is controlled by the parameter α which affects the negative resistance region and the hysteresis property of the ID model. In consequence, there is a parameter region where combinatorial optimization problems are solved at the 100% success rate.
|
open access publishing via
|
|
|
|
|
|
|
|