An adaptive visual neuronal model implementing competitive, temporally asymmetric Hebbian learning

Yang, Zhijun, Cameron, Katherine, Murray, Alan and Boonsobhak, Vasin (2006) An adaptive visual neuronal model implementing competitive, temporally asymmetric Hebbian learning. International Journal of Neural Systems, 16 (3). pp. 151-162. ISSN 0129-0657

Full text is not in this repository.

Abstract

A novel depth-from-motion vision model based on leaky integrate-and-fire (I&F) neurons incorporates the implications of recent neurophysiological findings into an algorithm for object discovery and depth analysis. Pulse-coupled I&F neurons capture the edges in an optical flow field and the associated time of travel of those edges is encoded as the neuron parameters, mainly the time constant of the membrane potential and synaptic weight. Correlations between spikes and their timing thus code depth in the visual field. Neurons have multiple output synapses connecting to neighbouring neurons with an initial Gaussian weight distribution. A temporally asymmetric learning rule is used to adapt the synaptic weights online, during which competitive behaviour emerges between the different input synapses of a neuron. It is shown that the competition mechanism can further improve the model performance. After training, the weights of synapses sourced from a neuron do not display a Gaussian distribution, having adapted to encode features of the scenes to which they have been exposed.

Item Type: Article
Research Areas: A. > School of Science and Technology > Design Engineering and Mathematics
Item ID: 9908
Useful Links:
Depositing User: Zhijun Yang
Date Deposited: 28 Jan 2013 05:24
Last Modified: 13 Oct 2016 14:25
URI: https://eprints.mdx.ac.uk/id/eprint/9908

Actions (login required)

Edit Item Edit Item