Skip Nav Destination
Close Modal
Update search
NARROW
Format
TocHeadingTitle
Date
Availability
1-2 of 2
Katarzyna Kozdon
Close
Follow your search
Access your saved searches in your account
Would you like to receive an alert when new items match your search?
Sort by
Proceedings Papers
. isal2020, ALIFE 2020: The 2020 Conference on Artificial Life702-711, (July 13–18, 2020) 10.1162/isal_a_00345
Abstract
View Paper
PDF
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 through regressive and progressive plasticity. In this paper, we explored the effects of structural plasticity on learning in spiking neural networks with spike-timing-dependent plasticity: first, we systematically analysed three synapse pruning approaches (random, weight-dependent and activity-dependent) and their effects on networks’ weights, spiking activity and performance on a clustering task. Then, we examined the use of a minimalistic evolutionary approach to develop growth rules for spiking neural networks with or without pruning. We found that pruning combined with a simple weight homeostasis mechanism can be used to reduce spiking neural networks’ size without a performance loss; pruning of weak connections increases the learning rate. Evolution of developmental rules led to a rapid fitness increase of the rudimentary embryo networks; addition of pruning significantly improved the learning rate of the model, and synaptic homeostasis preserved stable spiking activity in the networks even during drastic growth.
Proceedings Papers
. alife2018, ALIFE 2018: The 2018 Conference on Artificial Life276-283, (July 23–27, 2018) 10.1162/isal_a_00055
Abstract
View Paper
PDF
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 as well as the traditional machine learning approaches and their real-world applications are still limited. Various supervised and reinforcement learning methods for optimising spiking neural networks have been proposed, but more recently the evolutionary approach regained attention as a tool for training neural networks. Here, we describe a simple evolutionary approach for optimising spiking neural networks. This is the first published use of evolutionary algorithm to develop hyperparameters for fully unsupervised spike-timing-dependent learning for pattern clustering using spiking neural networks. Our results show that combining evolution and unsupervised learning leads to faster convergence on the optimal solutions, better stability of fit solutions and higher fitness of the whole population than using each approach separately.