Liam McDaid

TL;DR: A synaptic weight association training (SWAT) algorithm for spiking neural networks (SNNs) that merges the Bienenstock-Cooper-Munro (BCM) learning rule with spike timing dependent plasticity (STDP) and yields a unimodal weight distribution.

TL;DR: The architecture employs an approximation to the fuzzy reasoning system to considerably reduce the dimensions of the network as compared to similar approaches, demonstrating the advantage of the neurofuzzy approach and highlighting the advantages of the architecture for hardware realisations.

TL;DR: Results show that slow inward currents cause synchronized postsynaptic activity in remote neurons and subsequently allow Spike-Timing-Dependent Plasticity based learning to occur at the associated synapses, and that bidirectional communication between neurons and astrocytes underpins dynamic coordination between neuron clusters.

TL;DR: A novel hierarchical network-on-chip (H-NoC) architecture for SNN hardware is presented, which aims to address the scalability issue by creating a modular array of clusters of neurons using a hierarchical structure of low and high-level routers.

TL;DR: A novel field programmable neural network architecture (EMBRACE), incorporating low-power analogue spiking neurons, interconnected using a Network-on-Chip architecture is proposed, and the performance of the architecture is discussed.