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
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 language | English |
---|---|
Pages | 20-23 |
Number of pages | 4 |
Publication status | Published - 2019 |
Keywords
- SpiNNaker
- Neuromorphic computing
- Spiking Neural Network
- structural plasticity
- synaptic rewiring
- topographic maps