Beyond PDP: The Frequency Modulation Neural Network Architecture
Abstract
This paper proposes the Frequency Modulation Neural Network as an alternative to current neural-net models. This proposal is for an architecture of a heterogeneous neural-network in which information is propagated using frequency modulation of pulses oscillated by groups of neurons. The FMNN model enables operations including variable-binding, sequential recognitions and predictions. The use of FM signals for communication among neural clusters also enables the model to avoid communication bottlenecks arising in most massively parallel computer architectures.
Cite
Text
Tomabechi and Kitano. "Beyond PDP: The Frequency Modulation Neural Network Architecture." International Joint Conference on Artificial Intelligence, 1989.Markdown
[Tomabechi and Kitano. "Beyond PDP: The Frequency Modulation Neural Network Architecture." International Joint Conference on Artificial Intelligence, 1989.](https://mlanthology.org/ijcai/1989/tomabechi1989ijcai-beyond/)BibTeX
@inproceedings{tomabechi1989ijcai-beyond,
title = {{Beyond PDP: The Frequency Modulation Neural Network Architecture}},
author = {Tomabechi, Hideto and Kitano, Hiroaki},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1989},
pages = {186-192},
url = {https://mlanthology.org/ijcai/1989/tomabechi1989ijcai-beyond/}
}