Frequency division multiplexing in analogue neural network

Hayes-Gill, Barrie; Craven, Michael

Abstract

Frequency division multiplexing has been studied as a means of communication between neural layers in an analogue multilayered perceptron neural network architecture, trained using the back-propagation learning algorithm. Simulation results on network learning and generalisation show that the neural network is tolerant to as much as 50% overlap of frequency responses of filters used in demultiplexing. Thus, the number of communication channels available is considerably increased.

Citation

Hayes-Gill, B., & Craven, M. (1991). Frequency division multiplexing in analogue neural network. Electronics Letters, 27(11), 918-920. https://doi.org/10.1049/el%3A19910575

• Journal Article Type: Article
• Publication Date: May 23, 1991
• Deposit Date: Nov 27, 2018
• Journal: Electronics Letters
• Print ISSN: 0013-5194
• Electronic ISSN: 1350-911X
• Publisher: Institution of Engineering and Technology (IET)
• Peer Reviewed: Peer Reviewed
• Volume: 27
• Issue: 11
• Pages: 918-920
• DOI: https://doi.org/10.1049/el%3A19910575
• Public URL: https://nottingham-repository.worktribe.com/output/1282280
• Publisher URL: https://ieeexplore.ieee.org/abstract/document/78092