Self-organizing system obtaining communication ability

Primitive model for language generation

Abstract

As one of the synthetic approaches to brain functions, the possibility is discussed that two intellectual robots could make “words” for themselves and come to communicate with each other. Associatron, a model for associative memory with a neural network structure, is used as the memory in the brain, and information from the outer world is accumulated in it. Concepts regarding objects and attributes are extracted from the stored information, where the Associatron properties are utilized. The robots give specific names to the concepts and inter-change them with each other. When the robots have the same experience at the same time, they modify their own words according to what the other robot says. As they repeat common experiences, the differences between the words become smaller and smaller, and finally the robots agree on a word for each object. At this stage, the robots can exchange information with their words and each can act accordingly on the word from the other. This study shows that the self-organizing system with the above function can be constructed as a neural network model.

This is a preview of subscription content, access via your institution.

References

  1. Doya K, Nakano K (1985) Self-organizing system obtaining behavioral pattern. SICE (the Society of Instrument and Control Engineers) 3rd Knowledge Engineering Symposium (in japanese)

  2. Hebb DO (1949) The organization of behavior. Wiley, New York

    Google Scholar 

  3. Nakano K (1969) Associatron and its application. IECE (the Institute of Electronics and Communication Engineers of Japan) Technical Report, IT 69-27 (in Japanese)

  4. Nakano K (1972) Associatron — a model of associative memory. IEEE Trans SMC-2:381–388

    Google Scholar 

  5. Nakano K (1984) Modeling for sensory information processing. J Robot Soc Jpn 2:67–72 (in Japanese)

    Google Scholar 

  6. Nakano K, Ohmori T, Arita T, Takeda S (1984) On a self-organizing system obtaining the ability to exchange information between information processors. SICE 2nd Knowledge Engineering Symposium (in Japanese)

  7. Ohmori T, Nakano K (1984) Model of visual neural system with self-organizing cells. Trans SICE 20:56–63 (in Japanese)

    Google Scholar 

Download references

Author information

Affiliations

Authors

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Nakano, K., Sakaguchi, Y., Isotani, R. et al. Self-organizing system obtaining communication ability. Biol. Cybern. 58, 417–425 (1988). https://doi.org/10.1007/BF00361348

Download citation

Keywords

  • Neural Network
  • Network Model
  • Network Structure
  • Brain Function
  • Neural Network Model