-transparent.png){kind=logo}
An optical associative neural network with a stochastic thresholding procedure has been demonstrated. The use of stochastic processing drastically improved the convergence rate into the correct global minima (recognition rate). The properties of undesirable spurious minima were also investigated. It was found that the spurious minima were represented as the mixed states of the stored vectors. A useful method to estimate the required noise level to vanish the spurious minima is described.
| UI | MeSH Term | Description | Entries |
|---|
Related Publications
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
January 1991,
Neural computation,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
February 1989,
Optics letters,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
January 2020,
PeerJ. Computer science,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
February 2010,
Behavior research methods,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
January 1984,
Biological cybernetics,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
May 2023,
IEEE transactions on neural networks and learning systems,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
January 1991,
Optics letters,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
August 2023,
Cognitive neurodynamics,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
March 2016,
IEEE transactions on neural networks and learning systems,
J Ohta, and
S Tai, and
M Oita, and
K Kuroda, and
K Kyuma, and
K Hamanaka
June 2017,
Neural computation,
