Publication: Architectural Plasticity in Spiking Neural Networks

Architectural Plasticity in Spiking Neural Networks In Proceedings of The Artificial Life Conference 2020. MIT Press Montreal, Canada. 13-18 July 2020. Abstract— We can talk about learning optimisation in terms of three biological processes: evolution, development and learning. It has been argued that all three are necessary for intelligence to emerge. Together, they shape the brain …

Publication: Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity

Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity The Developmental Neural Networks Workshop. The 2019 Conference on Artificial Life (ALife 2019). Newcastle, United Kingdom. 29 July - 2 August 2019. Abstract— Maintaining the ability to fire sparsely is crucial for information encoding in neural networks. Additionally, spiking homeostasis is vital …

Publication: The Evolution of Training hyperparameters for SNNs with Hebbian Learning. (video)

The Evolution of Training Parameters for Spiking Neural Networks with Hebbian Learning In Proceedings of The Artificial Life Conference 2018. MIT Press Tokyo, Japan. 23-27 July 2018. Abstract— Spiking neural networks, thanks to their sensitivity to the timing of the inputs, are a promising tool for unsupervised processing of spatio-temporal data. However, they do not perform …

Publication: Wide Learning. SNN ensembles.

Wide Learning: Using an Ensemble of Biologically-Plausible Spiking Neural Networks for Unsupervised Parallel Classification of Spatio-Temporal Patterns In Proc. 2017 IEEE Symposium Series on Computational Intelligence (SSCI) Honolulu, Hawaii. 27 Nov-1 Dec 2017. Abstract— Spiking neural networks have been previously used to perform tasks such as object recognition without supervision. One of the concerns relating …