Deep Learning in Spiking Neural Networks

Abstract

In recent years, deep learning has been a revolution in the field of machine learning, for computer vision in particular. In this approach, a deep (multilayer) artificial neural network (ANN) is trained in a supervised manner using backpropagation. Huge amounts of labeled examples are required, but the resulting classification accuracy is truly impressive, sometimes outperforming humans. Neurons in an ANN are characterized by a single, static, continuous-valued activation. Yet biological neurons use discrete spikes to compute and transmit information, and the spike times, in addition to the spike rates, matter. Spiking neural networks (SNNs) are thus more biologically realistic than ANNs, and arguably the only viable option if one wants to understand how the brain computes. SNNs are also more hardware friendly and energy-efficient than ANNs, and are thus appealing for technology, especially for portable devices. However, training deep SNNs remains a challenge. Spiking neurons' transfer function is usually non-differentiable, which prevents using backpropagation. Here we review recent supervised and unsupervised methods to train deep SNNs, and compare them in terms of accuracy, but also computational cost and hardware friendliness. The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while the SNNs typically require much fewer operations.

References in corpus (32)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Fully Convolutional Networks for Semantic Segmentation
• 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
• SuperSpike: Supervised learning in multi-layer spiking neural networks
• Towards Biologically Plausible Deep Learning
• Neuromorphic Deep Learning Machines
• A sparse coding model with synaptically local plasticity and spiking neurons can account for the diverse shapes of V1 simple cell receptive fields
• Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems
• Spiking Deep Networks with LIF Neurons
• First-spike based visual categorization using reward-modulated STDP
• Supervised Learning in Multilayer Spiking Neural Networks
• Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
• Motor control by precisely timed spike patterns
• Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition
• Emergence of Compositional Representations in Restricted Boltzmann Machines
• Training Spiking Deep Networks for Neuromorphic Hardware
• Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
• Phase Diagram of Restricted Boltzmann Machines and Generalised Hopfield Networks with Arbitrary Priors
• Phase transitions in Restricted Boltzmann Machines with generic priors
• A Spiking Network that Learns to Extract Spike Signatures from Speech Signals
• Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning
• Spatiotemporal dynamics and reliable computations in recurrent spiking neural networks
• Deep Spiking Networks
• Acquisition of Visual Features Through Probabilistic Spike-Timing-Dependent Plasticity
• Representation Learning using Event-based STDP
• Humans and deep networks largely agree on which kinds of variation make object recognition harder
• Cortical microcircuits as gated-recurrent neural networks
• MT-Spike: A Multilayer Time-based Spiking Neuromorphic Architecture with Temporal Error Backpropagation

Cited by in corpus (132)

• Artificial neural networks for neuroscientists: A primer
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Deep Residual Learning in Spiking Neural Networks
• 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
• Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
• Surrogate Gradient Learning in Spiking Neural Networks
• Learning to Detect Objects with a 1 Megapixel Event Camera
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
• Biologically plausible deep learning -- but how far can we go with shallow networks?
• Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networks
• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• Applications and Techniques for Fast Machine Learning in Science
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks
• Efficient training and design of photonic neural network through neuroevolution
• Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemes
• Partial success in closing the gap between human and machine vision
• Collective and synchronous dynamics of photonic spiking neurons
• Q-SpiNN: A Framework for Quantizing Spiking Neural Networks
• Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data
• Neuromorphic scaling advantages for energy-efficient random walk computation
• Advances in Quantum Deep Learning: An Overview
• Design Space Exploration of Hardware Spiking Neurons for Embedded Artificial Intelligence
• Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches?
• A Nanoscale Room-Temperature Multilayer Skyrmionic Synapse for Deep Spiking Neural Networks
• The Backpropagation Algorithm Implemented on Spiking Neuromorphic Hardware
• Cryogenic Neuromorphic Hardware
• ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories
• Efficient Hardware Acceleration of Sparsely Active Convolutional Spiking Neural Networks
• Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks
• Oscillator Circuit for Spike Neural Network with Sigmoid Like Activation Function and Firing Rate Coding
• Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection
• A bio-inspired bistable recurrent cell allows for long-lasting memory
• EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems
• High-parallelism Inception-like Spiking Neural Networks for Unsupervised Feature Learning
• Integration of Leaky-Integrate-and-Fire-Neurons in Deep Learning Architectures
• Stochasticity and Robustness in Spiking Neural Networks
• Spiking neural networks trained via proxy
• Continuous learning of spiking networks trained with local rules
• Antiferromagnet-Based Neuromorphics Using Dynamics of Topological Charges
• Evolved Neuromorphic Control for High Speed Divergence-based Landings of MAVs
• Robust trajectory generation for robotic control on the neuromorphic research chip Loihi
• A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks
• Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance
• A compact neuromorphic system for ultra-energy-efficient, on-device robot localization
• lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents
• SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with Spikes
• Simulation of memristive synapses and neuromorphic computing on a quantum computer
• Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data
• SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks
• Self-Supervised Representation Learning for Detection of ACL Tear Injury in Knee MR Videos
• Temporal State Machines: Using temporal memory to stitch time-based graph computations
• Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks
• Bio-inspired spike-based Hippocampus and Posterior Parietal Cortex models for robot navigation and environment pseudo-mapping
• Non-linear Neurons with Human-like Apical Dendrite Activations
• TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agents
• Deep Spiking Neural Network with Spike Count based Learning Rule
• Symbiosis of an artificial neural network and models of biological neurons: training and testing
• Neuromorphic In-Context Learning for Energy-Efficient MIMO Symbol Detection
• RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
• Learning on Hardware: A Tutorial on Neural Network Accelerators and Co-Processors
• Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks
• Neural Network Methods for Radiation Detectors and Imaging
• A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
• Efficient FPGA-accelerated Convolutional Neural Networks for Cloud Detection on CubeSats
• Gradient-Free Training of Recurrent Neural Networks using Random Perturbations
• Fast and energy-efficient neuromorphic deep learning with first-spike times
• Faster and Simpler SNN Simulation with Work Queues
• Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
• SpikePipe: Accelerated Training of Spiking Neural Networks via Inter-Layer Pipelining and Multiprocessor Scheduling
• SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems
• Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference
• Unsupervised Clustering of Time Series Signals using Neuromorphic Energy-Efficient Temporal Neural Networks
• Neural Population Coding for Effective Temporal Classification
• A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDP
• Spiking Inception Module for Multi-layer Unsupervised Spiking Neural Networks
• Hybrid Synaptic Structure for Spiking Neural Network Realization
• Deep Spiking Convolutional Neural Network for Single Object Localization Based On Deep Continuous Local Learning
• Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition
• Event-Driven Visual-Tactile Sensing and Learning for Robots
• Benchmarking Spiking Neural Network Learning Methods with Varying Locality
• Accelerating SNN Training with Stochastic Parallelizable Spiking Neurons
• Improving STDP-based Visual Feature Learning with Whitening
• A Dual-Memory Architecture for Reinforcement Learning on Neuromorphic Platforms
• Spike-based computation using classical recurrent neural networks
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks
• A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network
• Semi-supervised learning combining backpropagation and STDP: STDP enhances learning by backpropagation with a small amount of labeled data in a spiking neural network
• Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks
• SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments
• Spiking representation learning for associative memories
• A spiking photonic neural network of 40.000 neurons, trained with rank-order coding for leveraging sparsity
• Biologically Plausible Learning of Text Representation with Spiking Neural Networks
• Understanding the Functional Roles of Modelling Components in Spiking Neural Networks
• A Neuromorphic Paradigm for Online Unsupervised Clustering
• MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognition
• Tuning Convolutional Spiking Neural Network with Biologically-plausible Reward Propagation
• Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics
• A multi-agent evolutionary robotics framework to train spiking neural networks
• Towards the Next Generation of Retinal Neuroprosthesis: Visual Computation with Spikes
• A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data
• Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
• Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition
• A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection
• A New Neuromorphic Computing Approach for Epileptic Seizure Prediction
• Sequence learning in Associative Neuronal-Astrocytic Network
• Spiking Neural Networks with Single-Spike Temporal-Coded Neurons for Network Intrusion Detection
• SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking
• U-Net-Like Spiking Neural Networks for Single Image Dehazing
• Genetic Algorithmic Parameter Optimisation of a Recurrent Spiking Neural Network Model
• Learning to Act through Evolution of Neural Diversity in Random Neural Networks
• File Classification Based on Spiking Neural Networks
• Minibatch Processing in Spiking Neural Networks
• S3TC: Spiking Separated Spatial and Temporal Convolutions with Unsupervised STDP-based Learning for Action Recognition
• Effects of VLSI Circuit Constraints on Temporal-Coding Multilayer Spiking Neural Networks
• Learning without gradient descent encoded by the dynamics of a neurobiological model
• Accurate and Energy-Efficient Classification with Spiking Random Neural Network: Corrected and Expanded Version
• ScieNet: Deep Learning with Spike-assisted Contextual Information Extraction
• Fine-Pruning: A Biologically Inspired Algorithm for Personalization of Machine Learning Models
• Hyperdimensional Decoding of Spiking Neural Networks
• Linear Constraints Learning for Spiking Neurons
• 2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action Recognition
• Neural Network Degeneration and its Relationship to the Brain
• MAR: Efficient Large Language Models via Module-aware Architecture Refinement
• Latent Time-Adaptive Drift-Diffusion Model
• Bio-inspired Rhythmic Locomotion in a Six-Legged Robot
• Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking
• Action Recognition Using Supervised Spiking Neural Networks
• Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems
• The backpropagation-based recollection hypothesis: Backpropagated action potentials mediate recall, imagination, language understanding and naming