Local Sensory Signals Integration Learning
and
Some Models of Visual Systems
based on Temporal Smoothing Learning using Neural Network

Summary

Our visual sensor consists of many retinal neurons, each of which covers only a local receptive field. In order to recognize the object location as an analog value, we have to integrate visual signals from many retinal neurons. In our real world, objects usually move smoothly according to the equations of motion. If an output of a neural network which receives inputs from retinal neurons, changes smoothly along time, the output represents the object location as an analog value. Then the learning method has been proposed, which makes the output of the neural network become smooth, in other words, makes the second time derivative of the output become 0.

Key Words

unsupervised learning, sensor integration, temporal smoothness, neural network, smoothing learning

Reference

Katsunari Shibata, Yoichi Okabe:
Temporal Smoothing Learning,
Trans. IEE (The Institute of Electrical Engineers) of Japan, Vol. 117-C, No. 9, pp.1291-1299, 1997.9 (in Japanese)
柴田克成、岡部洋一 :

時間軸スムージング学習

電気学会論文誌Ｃ分冊, Vol. 117-C, No. 9, pp.1291-1299 (1997.9)

Katsunari Shibata & Yoichi Okabe:
Integration of Local Sensory Signals and Extraction of Spatial Information Based on Temporal Smoothing Learning,
J. of JNNS(Japan Neural Network Society), Vol. 3, No. 3, pp.98-105, 1996. 9 (in Japanese)
柴田克成、岡部洋一:

時間軸スムージング学習による局所センサ信号の統合と空間情報の抽出

日本神経回路学会誌, Vol. 3, No. 3, pp.98-105, 1996

K. Shibata and Y. Okabe : PS File (110kB in Japanese)

"Temporal Smoothing Learning and Integration of Local Sensory Signal"

"時間軸スムージング学習と局所センサ情報の統合"

日本神経回路学会第7回全国大会講演論文集 名古屋 Proc. of JNNS'97, pp.178-179, 1996

K. Shibata and Y. Okabe : PS File (39kB)

"Unsupervised Learning Method to Extract Object Locations from Local VisualSignals"

Proc. of ICNN'94 Orlando, vol.3, pp.1556-1559, 1994.7

K. Shibata and Y. Okabe : PS File (60kB)

"Some Models of Visual Systems based on Local Sensory Signals Integrateion Learning"

Proc. of ICNN'95 Perth, Vol.IV, pp.1986-1990, 1995.11