Bioinspired Artificial Intelligence optimisation using High-Performance Computing

Spiking neural networks (SNNs) mimic their biological counterparts more closely than their predecessors and are considered the third generation of artificial neural networks. This research introduces a new type of spiking neural network that draws inspiration and incorporates concepts from neuronal assemblies in the human brain. The proposed network, termed CDNA-SNN, assigns each neuron learnable values known as Class-Dependent Neuronal Activations (CDNAs), which indicate the neuron’s average relative spiking activity in response to samples from different classes. A new learning algorithm is also presented that categorises the neurons into different class assemblies based on their CDNAs. These neuronal assemblies are trained via a novel training method based on Spike-Timing Dependent Plasticity (STDP) to have high activity for their class and low firing rate for other classes. The results on multiple benchmarks indicate that the proposed network can achieve higher performance with considerably fewer network parameters than other SNNs in comparison.