A neural model for context-dependent sequence learning

Berthouze, Luc and Tijsseling, Adriaan (2006) A neural model for context-dependent sequence learning. Neural Processing Letters, 23 (1). pp. 27-45. ISSN 1370-4621

Full text not available from this repository.

Abstract

A novel neural network model is described that implements context-dependent learning of complex sequences. The model utilises leaky integrate-and-fire neurons to extract timing information from its input and modifies its weights using a learning rule with synaptic noise. Learning and recall phases are seamlessly integrated so that the network can gradually shift from learning to predicting its input. Experimental results using data from the real-world problem domain demonstrate that the use of context has three important benefits: (a) it prevents catastrophic interference during learning of multiple overlapping sequences, (b) it enables the completion of sequences from missing or noisy patterns, and (c) it provides a mechanism to selectively explore the space of learned sequences during free recall.

Item Type: Article
Additional Information: Originality: Novel neural network model that implements context-dependent learning of complex sequences. Learning and recall phases are seamlessly integrated. Rigour: Mathematical simulations based on data from the public domain. Significance: This biologically inspired model has three key features: it can learn multiple overlapping sequences; it preserves the timing of the sequences; it can complete incomplete or noisy sequences. Impact: The model is directly applicable to real-world applications, e.g., robotic applications, or usable as a component of a larger cognitive system.
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Luc Berthouze
Date Deposited: 06 Feb 2012 18:25
Last Modified: 06 Jul 2012 07:57
URI: http://sro.sussex.ac.uk/id/eprint/16278
📧 Request an update