Beyond PDP: The Frequency Modulation Neural Network Architecture

This paper proposes the Frequency Modulation Neural Network as an alternative to current neuralnet 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.

• Type: Conference
• Year: 1989
• Where: IJCAI
• Authors: Hideto Tomabechi, Hiroaki Kitano
• Keywords: Frequency Modulation, IJCAI 1989, IJCAI 2007, Model Enables Operations, Modulation Neural Network