Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding

Abstract

Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent attention has been focused on the development of supervised learning rules for spiking neural networks that utilise a temporal coding scheme. However, despite significant progress in this area, there still lack rules that have a theoretical basis, and yet can be considered biologically relevant. Here we examine the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code. As part of our analysis we examine two spike-based learning methods: one of which relies on an instantaneous error signal to modify synaptic weights in a network (INST rule), and the other one on a filtered error signal for smoother synaptic weight modifications (FILT rule). We test the accuracy of the solutions provided by each rule with respect to their temporal encoding precision, and then measure the maximum number of input patterns they can learn to memorise using the precise timings of individual spikes as an indication of their storage capacity. Our results demonstrate the high performance of FILT in most cases, underpinned by the rule's error-filtering mechanism, which is predicted to provide smooth convergence towards a desired solution during learning. We also find FILT to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision. In comparison with existing work, we determine the performance of FILT to be consistent with that of the highly efficient E-learning Chronotron, but with the distinct advantage that FILT is also implementable as an online method for increased biological realism.

26 pages, 10 figures, this version is published in PLoS ONE and incorporates reviewer comments

References in corpus (1)

• Encoding Spike Patterns in Multilayer Spiking Neural Networks

Cited by in corpus (15)

• SuperSpike: Supervised learning in multi-layer spiking neural networks
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
• Beyond spiking networks: the computational advantages of dendritic amplification and input segregation
• Target spiking patterns enable efficient and biologically plausible learning for complex temporal tasks
• VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner-Take-All Circuits
• Error-based or target-based? A unifying framework for learning in recurrent spiking networks
• A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow
• File Classification Based on Spiking Neural Networks
• SpinAPS: A High-Performance Spintronic Accelerator for Probabilistic Spiking Neural Networks
• Linear Constraints Learning for Spiking Neurons
• Supervised Learning in Temporally-Coded Spiking Neural Networks with Approximate Backpropagation
• An online supervised learning algorithm based on triple spikes for spiking neural networks
• Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing
• Pre-Synaptic Pool Modification (PSPM): A Supervised Learning Procedure for Spiking Neural Networks