UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Modification of Internal Representations as a Mechanism for Learning in Neural Systems

Wren, Ken Kangda; (1999) Modification of Internal Representations as a Mechanism for Learning in Neural Systems. Doctoral thesis (Ph.D), UCL (University College London). Green open access

[thumbnail of Modification_of_internal_repre.pdf] Text
Modification_of_internal_repre.pdf

Download (6MB)

Abstract

Description of Thesis Title: Modification of Internal Representations as a Mechanism for Learning in Neural Systems. 1. Incoming sensory signals are processed by hierarchically organised modules in the brain. In certain contexts, this may be modelled by a feedforward layered network of interconnected binary units. The activity patterns in the intermediate layers are internal representations. 2. A new learning algorithm uses projections from the desired output to modify internal representations. Biologically realistic 2-layer synaptic rules can then be applied to cause the associated input to evoke the modified representation(s) that are more readily trained to produce the target output. 3. Simulation is carried out on benchmark tasks for 3-layer feedforward networks. Comparisons with other popular algorithms are made. The results suggest that the new algorithm has better generalisation performance with faster or equal learning speed on the tasks simulated. 4. The learning algorithm is generalised to a multi-layer network setting, in which internal representations are dynamically constructed. 5. The above will be put into the context of efficient sensory coding that is based on Barlow’s ‘redundancy reduction’ proposal.

Type: Thesis (Doctoral)
Qualification: Ph.D
Title: Modification of Internal Representations as a Mechanism for Learning in Neural Systems
Open access status: An open access version is available from UCL Discovery
Language: English
Additional information: Thesis digitised by ProQuest.
URI: https://discovery.ucl.ac.uk/id/eprint/10104591
Downloads since deposit
16Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item