Multiple channel crosstalk removal using limited connectivity neural networks

Craven, Michael P.; Curtis, K. Mervyn; Hayes-Gill, Barrie R.

Abstract

Limited connectivity neural network architectures are investigated for the removal of crosstalk in systems using mutually overlapping sub-channels for the communication of multiple signals, either analogue or digital. The crosstalk error is modelled such that a fixed proportion of the signals in adjacent channels is added to the main signal. Different types of neural networks, trained using gradient descent algorithms, are tested as to their suitability for reducing the errors caused by a combination of crosstalk and additional gaussian noise. In particular we propose a single layer limited connectivity neural network since it promises to be the most easily implemented in hardware. A variable gain neuron structure is described which can be used for both analogue and digital data.

Citation

Craven, M. P., Curtis, K. M., & Hayes-Gill, B. R. Multiple channel crosstalk removal using limited connectivity neural networks. Presented at 3rd IEEE International Conference on Electronics, Circuits, and Systems (ICECS 96)

• Conference Name: 3rd IEEE International Conference on Electronics, Circuits, and Systems (ICECS 96)
• End Date: Oct 16, 1996
• Deposit Date: Feb 20, 2013
• Peer Reviewed: Peer Reviewed
• Keywords: neural networks, ANN, cross-talk, gradient descent, learning
• Public URL: https://nottingham-repository.worktribe.com/output/1024408
• Publisher URL: http://dx.doi.org/10.1109/ICECS.1996.584614
• Related Public URLs: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=584614
• Additional Information: © 1996 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.