Selective attention is a very important function for robots acting in the real world. In this function, not only attention itself, but also context extraction and retention are very intelligent processes and are not easily realized. In this article, an attention task is presented in which context information must be extracted from the first pattern presented, and using the context information, a recognition response must be generated from the second pattern presented. An Elman-type recurrent neural network is used to extract and retain the context information. The reinforcement signal that indicates whether the response is correct or not is the only signal given to the system during learning. By this simple learning process, the necessary context information got to be extracted and retained, and then the system changed to generate the correct responses. The function of associative memory was also observed in the feedback-loop in the Elman-type neural network. Furthermore the adaptive formation of basins was examined by varying the learning conditions.
[1]
阪口豊.
2-5 触知覚における感覚統合と能動的認識
,
1993
.
[2]
David Zipser,et al.
Recurrent Network Model of the Neural Mechanism of Short-Term Active Memory
,
1991,
Neural Computation.
[3]
Andrew McCallum,et al.
Learning to Use Selective Attention and Short-Term Memory in Sequential Tasks
,
1996
.
[4]
Geoffrey E. Hinton,et al.
Learning internal representations by error propagation
,
1986
.
[5]
Katsunari Shibata.
Formation of Attention and Associative Memory based on Reinforcement Learning
,
2001
.
[6]
Jeffrey L. Elman,et al.
Finding Structure in Time
,
1990,
Cogn. Sci..
[7]
Katsunari SHIBATA,et al.
Formation of Attention and Associative Memory Based on Recognition Learning
,
2002
.
[8]
P. Goldman-Rakic,et al.
Visuospatial coding in primate prefrontal neurons revealed by oculomotor paradigms.
,
1990,
Journal of neurophysiology.