A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rule

Abstract

Spiking neural networks (SNNs) possess energy-efficient potential due to event-based computation. However, supervised training of SNNs remains a challenge as spike activities are non-differentiable. Previous SNNs training methods can be generally categorized into two basic classes, i.e., backpropagation-like training methods and plasticity-based learning methods. The former methods are dependent on energy-inefficient real-valued computation and non-local transmission, as also required in artificial neural networks (ANNs), whereas the latter are either considered to be biologically implausible or exhibit poor performance. Hence, biologically plausible (bio-plausible) high-performance supervised learning (SL) methods for SNNs remain deficient. In this paper, we proposed a novel bio-plausible SNN model for SL based on the symmetric spike-timing dependent plasticity (sym-STDP) rule found in neuroscience. By combining the sym-STDP rule with bio-plausible synaptic scaling and intrinsic plasticity of the dynamic threshold, our SNN model implemented SL well and achieved good performance in the benchmark recognition task (MNIST dataset). To reveal the underlying mechanism of our SL model, we visualized both layer-based activities and synaptic weights using the t-distributed stochastic neighbor embedding (t-SNE) method after training and found that they were well clustered, thereby demonstrating excellent classification ability. Furthermore, to verify the robustness of our model, we trained it on another more realistic dataset (Fashion-MNIST), which also showed good performance. As the learning rules were bio-plausible and based purely on local spike events, our model could be easily applied to neuromorphic hardware for online training and may be helpful for understanding SL information processing at the synaptic level in biological neural systems.

arXiv comment29 pages, 6 figures

References in corpus (13)

• Deep Learning in Neural Networks: An Overview
• LSTM: A Search Space Odyssey
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Deep Learning in Spiking Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
• STDP-based spiking deep convolutional neural networks for object recognition
• Spiking Deep Networks with LIF Neurons
• Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
• Supervised Learning in Multilayer Spiking Neural Networks
• Formation of feedforward networks and frequency synchrony by spike-timing-dependent plasticity
• Spiking Deep Residual Network
• An STDP-Based Supervised Learning Algorithm for Spiking Neural Networks

Cited by in corpus (8)

• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemes
• Differential Mapping Spiking Neural Network for Sensor-Based Robot Control
• Paired Competing Neurons Improving STDP Supervised Local Learning In Spiking Neural Networks
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits
• Spiking Neural Predictive Coding for Continual Learning from Data Streams
• Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules
• BioLeaF: A Bio-plausible Learning Framework for Training of Spiking Neural Networks