Vision coincidence detection with STDP adaptation for Object recognition and depth analysis

Yang, Zhijun ORCID: https://orcid.org/0000-0003-2615-4297 and Murray, Alan (2004) Vision coincidence detection with STDP adaptation for Object recognition and depth analysis. In: Brain Inspired Cognitive Systems 2004. Smith, Leslie Samuel, Hussain, Amir and Aleksander, Igor, eds. University of Stirling Department of Computing Science and Mathematics. ISBN 9781857691993. [Book Section]

Abstract

A cognitive vision neuronal network based on leaky integrate-and-fire (LIF) neurons is proposed for object recognition and depth analysis. In this network every LIF neuron is able to capture the edge flowing through it and record the temporal information. If the neuron issues a spike, the temporal information will be encoded by the time constant of the spike potential and transferred to its successor neuron through synapses. The successor neuron, on reception of the spike, will check whether that edge arrives at its sensor. In the case that both events synchronise the successor neuron will fire to confirm the correct edge propagation. Meanwhile, in the process the spike-timing-dependent plasticity (STDP) is employed to achieve the suitable synapse efficacies to reject spurious edge propagation. On recognition of the effective CMOS realisation of LIF neuron, our model aims to be a biologically inspired neuromorphic system amenable to aVLSI implementation.

Actions (login required)

View Item

Statistics

DownloadsShow export options

Export as CSVXMLJSON

Activity Overview

6 month trend

0Downloads

6 month trend

411Hits

Additional statistics are available via IRStats2.