Paper Abstract and Keywords |
Presentation |
2007-03-15 14:50
A simulation study of a cortical neural network model for spatiotemporal pattern classification Hiromasa Yamashita, Tatsuo Togawa (Waseda Univ.) |
Abstract |
(in Japanese) |
(See Japanese page) |
(in English) |
Although a great many studies have been performed on artificial neural network systems, most of the proposed systems differ from the actual brain in their network structure and function. To achieve a network structure similar to the cerebral cortex, the new cortical neural network model was proposed in which neurons as threshold elements are arranged in a single layer having feedback through a “winner-takes-all” algorithm. Recruitment of a virgin neuron when no neuron responds to an input was also assumed. An unsupervised learning simulation was performed. Inputs consisted of 8-bit vectors applied sequentially, and a modified Hebbian learning scheme was assumed at the input connections of each neuron. It was confirmed that the learning converged so that excitation of a specific neuron occurred for each input among 7 to 56 combinations of successively applied two-input vectors. The data showed that this model achieved spatiotemporal pattern classification in an unsupervised manner. |
Keyword |
(in Japanese) |
(See Japanese page) |
(in English) |
cortical neural network / single-cell-representation / pattern classification / / / / / |
Reference Info. |
IEICE Tech. Rep., vol. 106, no. 591, MBE2006-128, pp. 41-44, March 2007. |
Paper # |
MBE2006-128 |
Date of Issue |
2007-03-08 (MBE) |
ISSN |
Print edition: ISSN 0913-5685 |
Download PDF |
|
Conference Information |
Committee |
MBE |
Conference Date |
2007-03-15 - 2007-03-16 |
Place (in Japanese) |
(See Japanese page) |
Place (in English) |
Tamagawa Univ. |
Topics (in Japanese) |
(See Japanese page) |
Topics (in English) |
|
Paper Information |
Registration To |
MBE |
Conference Code |
2007-03-MBE |
Language |
Japanese |
Title (in Japanese) |
(See Japanese page) |
Sub Title (in Japanese) |
(See Japanese page) |
Title (in English) |
A simulation study of a cortical neural network model for spatiotemporal pattern classification |
Sub Title (in English) |
|
Keyword(1) |
cortical neural network |
Keyword(2) |
single-cell-representation |
Keyword(3) |
pattern classification |
Keyword(4) |
|
Keyword(5) |
|
Keyword(6) |
|
Keyword(7) |
|
Keyword(8) |
|
1st Author's Name |
Hiromasa Yamashita |
1st Author's Affiliation |
Waseda University (Waseda Univ.) |
2nd Author's Name |
Tatsuo Togawa |
2nd Author's Affiliation |
Waseda University (Waseda Univ.) |
3rd Author's Name |
|
3rd Author's Affiliation |
() |
4th Author's Name |
|
4th Author's Affiliation |
() |
5th Author's Name |
|
5th Author's Affiliation |
() |
6th Author's Name |
|
6th Author's Affiliation |
() |
7th Author's Name |
|
7th Author's Affiliation |
() |
8th Author's Name |
|
8th Author's Affiliation |
() |
9th Author's Name |
|
9th Author's Affiliation |
() |
10th Author's Name |
|
10th Author's Affiliation |
() |
11th Author's Name |
|
11th Author's Affiliation |
() |
12th Author's Name |
|
12th Author's Affiliation |
() |
13th Author's Name |
|
13th Author's Affiliation |
() |
14th Author's Name |
|
14th Author's Affiliation |
() |
15th Author's Name |
|
15th Author's Affiliation |
() |
16th Author's Name |
|
16th Author's Affiliation |
() |
17th Author's Name |
|
17th Author's Affiliation |
() |
18th Author's Name |
|
18th Author's Affiliation |
() |
19th Author's Name |
|
19th Author's Affiliation |
() |
20th Author's Name |
|
20th Author's Affiliation |
() |
Speaker |
Author-1 |
Date Time |
2007-03-15 14:50:00 |
Presentation Time |
25 minutes |
Registration for |
MBE |
Paper # |
MBE2006-128 |
Volume (vol) |
vol.106 |
Number (no) |
no.591 |
Page |
pp.41-44 |
#Pages |
4 |
Date of Issue |
2007-03-08 (MBE) |