The Brain & Neural Networks
Online ISSN : 1883-0455
Print ISSN : 1340-766X
ISSN-L : 1340-766X
Learning of Active Perception Based on Reinforcement Learning
Katsunari ShibataTetsuo NishinoYoichi Okabe
Author information
JOURNAL FREE ACCESS

1996 Volume 3 Issue 4 Pages 126-134

Details
Abstract
The aim is to perform to realize a learning system for active perception using a neural network. It obtains inputs only from a movable visual sensor and learns both appropriate recognition and sensor motions for effective perception. The proposed learning method is based on reinforcement learning using reinforcement signals calculated from the recognition results. We conclude from simulations that it enables the system to move a visual sensor to the appropriate location and finally classify presented patterns correctly. The recognition rate was better than that in a simulation for comparison where the sensor was fixed at the initial location.
Content from these authors
© 1996 Japanese Neural Network Society
Previous article Next article
feedback
Top