| Project/Area Number |
02455017
|
|---|
| Research Category |
Grant-in-Aid for General Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
広領域
|
|---|
| Research Institution | Kyushu Institute of Technology |
|---|
Principal Investigator |
YASUI Syozo Kyushu Inst. of Tech., Dept. of Control Engineering and Science, Professor, 情報工学部, 教授 (50132741)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
FURUKAWA Tetsuo Kyushu Inst. of Tech., Dept. of Control Engineering and Science, Research Associ, 情報工学部, 助手 (50219101)
YAGI Tetsuya Kyushu Inst. of Tech., Dept. of Control Engineering and Science, Associate Profe, 情報工学部, 助教授 (50183976)
NIIJIMA Koichi Kyushu Inst. of Tech., Dept. of Control Engineering and Science, Professor, 情報工学部, 教授 (30047881)
|
|---|
| Project Period (FY) |
1990 – 1992
|
| Keywords | Vision / Neurophysiology / Synapse / Retina / Pattern Recognition / Associative Memory / Learning Algorithm / 学習 |
|---|
| Research Abstract |
(1) The synaptic transmission from short-wavelength cones to H1 horizontal cells (H1HCs) in the carp retina is found to be of a conductance-decrease type with APB as an agonist. The synapse provides a new plasticity scheme for the lateral signal transmission across the outer retina. This mechanism can explain the old question of why the H1HC receptive field under light-adapted condition is narrower with blue/green lights than with red stimuli.
(2) Center-surround opponent receptive fields (CSRF) emerge in a 3-1ayerbackpropagation neural network (NN), as a result of edge-detection learning. The CSRF structure changes in such a way as to increase detectability of edges in the noise-corrupted input patterns. The same kind of SN-dependent plasticity exists in real visual systems, with retinal bipolar cells as well as certain interneurons in the fly compound eyes.
(3) An adaptive spatial filter for visual image processing has been developed, in part by applying the plasticity mechanisms of (1). The VLSI fabricated operates to solve a regularization problem automatically.
(4) An autoassociative memory network is constructed and it is analyzed on the basis of the contraction mapping principle. Large domains of attraction are found to exist, and any noisy pattern in such a domain can be recognized as one of the stored patterns. The network has been applied successfully to character and color-picture recognition problems.
(5) A new algorithm is devised to eliminate dynamically unnecessary connections in NN. While the performance error is being minimized, redundancy of neural connections can be removed by applying a mutual suppressionrule over input synaptic weight parameters at each synapse.
|
