Genomic and proteomic sequence recognition using a connectionist inference model.

Bavan, A. S. and Ford, Martyn and Kalatzi, Melina (2000) Genomic and proteomic sequence recognition using a connectionist inference model. Journal of chemical technology and biotechnology, 75 (10). pp. 901-912. ISSN 0264-3413

Full text is not in this repository.

Abstract

In this paper a proposal for implementing a connectionist associative memory model (CAMM) based on a novel approach for recognising sequences is presented. The objective of the CAMM is to satisfy medium-high capacity and the retrieval of an arbitrary number of multiple associative memories that satisfy the stimulus input. The architecture is constructed on-the-fly and is dependent on the information in the training set. The model is composed of two stages; StageI and StageII. StageI is concerned with the development of a state space graph representing the training set and embedding that graph in a connectionist model. During retrieval a graph is produced that represents the candidate solutions; some spurious memories may infiltrate the solution space which is removed in StageII using conventional techniques.

Item Type: Article
Research Areas: A. > School of Science and Technology > Computer and Communications Engineering
Item ID: 2335
Useful Links:
Depositing User: Repository team
Date Deposited: 18 May 2009 15:21
Last Modified: 15 Feb 2016 15:06
URI: http://eprints.mdx.ac.uk/id/eprint/2335

Actions (login required)

Edit Item Edit Item