-transparent.png){kind=logo}
This paper proposes a parallel distributed processing model with local space-invariant interconnections, which is more readily implemented by optics and is able to classify patterns correctly, even if they have been shifted or distorted. Error backpropagation is used as a training algorithm. Computer simulation results presented indicate that the processing is effective and the network can deal with the shifted or distorted patterns. Moreover, the optical implementation architecture using matched filters for the model is discussed.
| UI | MeSH Term | Description | Entries |
|---|
Related Publications
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
January 1998,
Applied optics,
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
March 1990,
Applied optics,
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
March 1990,
Applied optics,
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
October 1987,
Applied optics,
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
January 2023,
Network neuroscience (Cambridge, Mass.),
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
January 1998,
Applied optics,
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
May 1990,
Applied optics,
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
November 1988,
Applied optics,
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
January 1986,
Nature,
W Zhang, and
K Itoh, and
J Tanida, and
Y Ichioka
May 1995,
Applied optics,
