Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks

Abstract

The primate visual system has inspired the development of deep artificial neural networks, which have revolutionized the computer vision domain. Yet these networks are much less energy-efficient than their biological counterparts, and they are typically trained with backpropagation, which is extremely data-hungry. To address these limitations, we used a deep convolutional spiking neural network (DCSNN) and a latency-coding scheme. We trained it using a combination of spike-timing-dependent plasticity (STDP) for the lower layers and reward-modulated STDP (R-STDP) for the higher ones. In short, with R-STDP a correct (resp. incorrect) decision leads to STDP (resp. anti-STDP). This approach led to an accuracy of $97.2\%$ on MNIST, without requiring an external classifier. In addition, we demonstrated that R-STDP extracts features that are diagnostic for the task at hand, and discards the other ones, whereas STDP extracts any feature that repeats. Finally, our approach is biologically plausible, hardware friendly, and energy-efficient.

arXiv commentPattern Recognition (2019)

References in corpus (15)

• Deep Learning in Spiking Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• STDP-based spiking deep convolutional neural networks for object recognition
• Neuromorphic Deep Learning Machines
• Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems
• First-spike based visual categorization using reward-modulated STDP
• Online Learning: A Comprehensive Survey
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning
• Deep Spiking Networks
• Acquisition of Visual Features Through Probabilistic Spike-Timing-Dependent Plasticity
• STDP allows close-to-optimal spatiotemporal spike pattern detection by single coincidence detector neurons
• Optimal localist and distributed coding of spatiotemporal spike patterns through STDP and coincidence detection
• Deep Convolutional Spiking Neural Networks for Image Classification
• A wake-sleep algorithm for recurrent, spiking neural networks

Cited by in corpus (22)

• S4NN: temporal backpropagation for spiking neural networks with one spike per neuron
• A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rule
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network
• Continuous learning of spiking networks trained with local rules
• Thalamo-cortical spiking model of incremental learning combining perception, context and NREM-sleep-mediated noise-resilience
• SpikePropamine: Differentiable Plasticity in Spiking Neural Networks
• Finite Meta-Dynamic Neurons in Spiking Neural Networks for Spatio-temporal Learning
• Target spiking patterns enable efficient and biologically plausible learning for complex temporal tasks
• Paired Competing Neurons Improving STDP Supervised Local Learning In Spiking Neural Networks
• Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
• Unsupervised Clustering of Time Series Signals using Neuromorphic Energy-Efficient Temporal Neural Networks
• Direct CMOS Implementation of Neuromorphic Temporal Neural Networks for Sensory Processing
• Energy efficiency analysis of Spiking Neural Networks for space applications
• Error-based or target-based? A unifying framework for learning in recurrent spiking networks
• Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks
• Spiking Neural Predictive Coding for Continual Learning from Data Streams
• Exploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks
• Ensembles of Spiking Neural Networks
• Tuning Convolutional Spiking Neural Network with Biologically-plausible Reward Propagation
• A Microarchitecture Implementation Framework for Online Learning with Temporal Neural Networks