Beyond PDP: the frequency modulation neural network architecture

Authors:
Hideto Tomabechi;Hiroaki Kitano
Affiliations:
Center for Machine Translation, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA and Laboratory for Computational Linguistics, Carnegie Mellon University;NEC Corporation and Center for Machine Translation, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA
Venue:
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Year:
1989

Citing 11
Cited 0

MULTILISP: a language for concurrent symbolic computation

ACM Transactions on Programming Languages and Systems (TOPLAS)
The connection machine

The connection machine
A neural cocktail-party processor

Biological Cybernetics
Certain aspects of the anatomy and physiology of the cerebral cortex

Parallel distributed processing: explorations in the microstructure of cognition, vol. 2
Open questions about computation in cerebral cortex

Parallel distributed processing: explorations in the microstructure of cognition, vol. 2
Modeling small oscillating biological networks in analog VLSI

Advances in neural information processing systems 1
A general framework for parallel distributed processing

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Integrating Marker Passing and Problem Solving: A Spreading Activation Approach to Improved Choice in Planning

Integrating Marker Passing and Problem Solving: A Spreading Activation Approach to Improved Choice in Planning
Ambiguity resolution in the dmTrans Plus

EACL '89 Proceedings of the fourth conference on European chapter of the Association for Computational Linguistics
Parsing noisy sentences

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2
Application of the Direct Memory Access paradigm to natural language interfaces to knowledge-based systems

COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2

Quantified Score

Hi-index	0.00

Visualization

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.