Event-based computation: Unsupervised elementary motion decomposition

Petrut Bogdan, Garibaldi Pineda Garcia, Simon Davidson, Michael Hopkins, Robert James, Stephen Furber

Research output: Contribution to conferenceAbstractpeer-review

134 Downloads (Pure)

Abstract

Fast, localised motion detection is crucial for an
efficient attention mechanism. We show that modelling a network
capable of such motion detection can be performed using spiking
neural networks simulated on many-core neuromorphic hardware. Moreover, highly sensitive neurons arise from the presented
network architecture through unsupervised self-organisation. We
use a synaptic rewiring rule which has been shown to enable
the formation and refinement of neural topographic maps. Our
extension allows newly formed synapses to be initialised with a
delay drawn from a uniform distribution. Repeated exposure to
moving bars enables neurons to be sensitised to a preferred direction of movement. Incorporating heterogeneous delays results in
more sensitive neural responses. A readout mechanism involving
a neuron for each learnt motion is sufficient to establish the input
stimulus class
Original languageEnglish
Pages20-23
Number of pages4
Publication statusPublished - 2019

Keywords

  • SpiNNaker
  • Neuromorphic computing
  • Spiking Neural Network
  • structural plasticity
  • synaptic rewiring
  • topographic maps

Fingerprint

Dive into the research topics of 'Event-based computation: Unsupervised elementary motion decomposition'. Together they form a unique fingerprint.

Cite this