University of Sussex
Browse

File(s) not publicly available

A neural model for context-dependent sequence learning

journal contribution
posted on 2023-06-07, 19:57 authored by Luc BerthouzeLuc Berthouze, Adriaan Tijsseling
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.

History

Publication status

  • Published

Journal

Neural Processing Letters

ISSN

1370-4621

Publisher

Springer Verlag

Issue

1

Volume

23

Page range

27-45

Pages

19.0

Department affiliated with

  • Informatics Publications

Notes

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.

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2012-02-06

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC