Post and pre-compensatory Hebbian Learning for categorisation
Article
Huyck, C. and Mitchell, I. 2014. Post and pre-compensatory Hebbian Learning for categorisation. Cognitive Neurodynamics. 8 (4), pp. 299-311. https://doi.org/10.1007/s11571-014-9282-4
Type | Article |
---|---|
Title | Post and pre-compensatory Hebbian Learning for categorisation |
Authors | Huyck, C. and Mitchell, I. |
Abstract | A system with some degree of biological plausibility is developed to categorise items from a widely used machine learning benchmark. The system uses fatiguing leaky integrate and fire neurons, a relatively coarse point model that roughly duplicates biological spiking properties; this allows spontaneous firing based on hypo-fatigue so that neurons not directly stimulated by the environment may be included in the circuit. A novel compensatory Hebbian learning algorithm is used that considers the total synaptic weight coming into a neuron. The network is unsupervised and entirely self-organising. This is relatively effective as a machine learning algorithm, categorising with just neurons, and the performance is comparable with a Kohonen map. However the learning algorithm is not stable, and behaviour decays as length of training increases. Variables including learning rate, inhibition and topology are explored leading to stable systems driven by the environment. The model is thus a reasonable next step toward a full neural memory model. |
Keywords | Compensatory; Hebbian learning; Categorisation ; Spontaneous neural spiking ; Neural fatigue; Point neural model; Self-organisation |
Research Group | Artificial Intelligence group |
Publisher | Springer |
Journal | Cognitive Neurodynamics |
ISSN | 1871-4080 |
Electronic | 1871-4099 |
Publication dates | |
Online | 30 Jan 2014 |
31 Aug 2014 | |
Publication process dates | |
Deposited | 23 Apr 2015 |
Accepted | 22 Jan 2014 |
Output status | Published |
Digital Object Identifier (DOI) | https://doi.org/10.1007/s11571-014-9282-4 |
Web of Science identifier | WOS:000339010900004 |
Language | English |
https://repository.mdx.ac.uk/item/85101
47
total views0
total downloads1
views this month0
downloads this month