Meng, Hongying and Appiah, Kofi and Hunter, Andrew and Yue, Shigang and Hobden, Mervyn and Priestley, Nigel and Hobden, Peter and Pettit, Cy (2009) A modified sparse distributed memory model for extracting clean patterns from noisy inputs. In: IEEE International Joint Conference on Neural Networks (IJCNN 2009), Atlanta, USA..

	PDF IJCNN_419.pdf Restricted to Repository staff only Download (138Kb)
	PDF 05178873_IJCNN.pdf Download (6Mb)

Abstract

Abstract—The Sparse Distributed Memory (SDM) proposed by Kanerva provides a simple model for human long-term memory, with a strong underlying mathematical theory. However, there are problematic features in the original SDM model that affect its efficiency and performance in real world applications and for hardware implementation. In this paper, we propose modifications to the SDM model that improve its efficiency and performance in pattern recall. First, the address matrix is built using training samples rather than random binary sequences. This improves the recall performance significantly. Second, the content matrix is modified using a simple tri-state logic rule. This reduces the storage requirements of the SDM and simplifies the implementation logic, making it suitable for hardware implementation. The modified model has been tested using pattern recall experiments. It is found that the modified model can recall clean patterns very well from noisy inputs.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	Abstract—The Sparse Distributed Memory (SDM) proposed by Kanerva provides a simple model for human long-term memory, with a strong underlying mathematical theory. However, there are problematic features in the original SDM model that affect its efficiency and performance in real world applications and for hardware implementation. In this paper, we propose modifications to the SDM model that improve its efficiency and performance in pattern recall. First, the address matrix is built using training samples rather than random binary sequences. This improves the recall performance significantly. Second, the content matrix is modified using a simple tri-state logic rule. This reduces the storage requirements of the SDM and simplifies the implementation logic, making it suitable for hardware implementation. The modified model has been tested using pattern recall experiments. It is found that the modified model can recall clean patterns very well from noisy inputs.
Keywords:	Neural networks, SDM, Memory, Digital signal processing, Pattern recognition
Subjects:	G Mathematical and Computer Sciences > G750 Cognitive Modelling G Mathematical and Computer Sciences > G700 Artificial Intelligence G Mathematical and Computer Sciences > G400 Computer Science G Mathematical and Computer Sciences > G730 Neural Computing
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Users 503819 not found.
Date Deposited:	12 Aug 2009 12:51
Last Modified:	13 Mar 2013 08:32
URI:	http://eprints.lincoln.ac.uk/id/eprint/1879

Actions (login required)

View Item