STDP-based spiking deep convolutional neural networks for object recognition

Abstract

Previous studies have shown that spike-timing-dependent plasticity (STDP) can be used in spiking neural networks (SNN) to extract visual features of low or intermediate complexity in an unsupervised manner. These studies, however, used relatively shallow architectures, and only one layer was trainable. Another line of research has demonstrated - using rate-based neural networks trained with back-propagation - that having many layers increases the recognition robustness, an approach known as deep learning. We thus designed a deep SNN, comprising several convolutional (trainable with STDP) and pooling layers. We used a temporal coding scheme where the most strongly activated neurons fire first, and less activated neurons fire later or not at all. The network was exposed to natural images. Thanks to STDP, neurons progressively learned features corresponding to prototypical patterns that were both salient and frequent. Only a few tens of examples per category were required and no label was needed. After learning, the complexity of the extracted features increased along the hierarchy, from edge detectors in the first layer to object prototypes in the last layer. Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron. More generally, the activity of a few hundreds of such neurons contained robust category information, as demonstrated using a classifier on Caltech 101, ETH-80, and MNIST databases. We also demonstrate the superiority of STDP over other unsupervised techniques such as random crops (HMAX) or auto-encoders. Taken together, our results suggest that the combination of STDP with latency coding may be a key to understanding the way that the primate visual system learns, its remarkable processing speed and its low energy consumption.

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
• Spiking Deep Networks with LIF Neurons
• Humans and deep networks largely agree on which kinds of variation make object recognition harder

Cited by in corpus (79)

• Deep Learning in Spiking Neural Networks
• Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Spiking Neural Networks Hardware Implementations and Challenges: a Survey
• First-spike based visual categorization using reward-modulated STDP
• S4NN: temporal backpropagation for spiking neural networks with one spike per neuron
• Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception
• 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
• Ultra Low-Power and Real-time ECG Classification Based on STDP and R-STDP Neural Networks for Wearable Devices
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• Biologically plausible deep learning -- but how far can we go with shallow networks?
• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain
• Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemes
• Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning
• Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision
• Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data
• 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?
• Visual Question Answering for Cultural Heritage
• Representation Learning using Event-based STDP
• RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network
• Hardware Implementation of Spiking Neural Networks Using Time-To-First-Spike Encoding
• Stochasticity from function -- why the Bayesian brain may need no noise
• High-parallelism Inception-like Spiking Neural Networks for Unsupervised Feature Learning
• Voltage-Dependent Synaptic Plasticity (VDSP): Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential
• ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware
• Continuous learning of spiking networks trained with local rules
• Dendritic-Inspired Processing Enables Bio-Plausible STDP in Compound Binary Synapses
• Spiking neural networks trained via proxy
• Optimal localist and distributed coding of spatiotemporal spike patterns through STDP and coincidence detection
• Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
• 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
• Convolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks
• SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks
• Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data
• Deep Spiking Neural Network with Spike Count based Learning Rule
• SpikePropamine: Differentiable Plasticity in Spiking Neural Networks
• Precise spiking motifs in neurobiological and neuromorphic data
• Finite Meta-Dynamic Neurons in Spiking Neural Networks for Spatio-temporal Learning
• Connection Pruning for Deep Spiking Neural Networks with On-Chip Learning
• Paired Competing Neurons Improving STDP Supervised Local Learning In Spiking Neural Networks
• Fast and energy-efficient neuromorphic deep learning with first-spike times
• Fractional-order spike-timing-dependent gradient descent for multi-layer spiking neural networks
• Unsupervised Clustering of Time Series Signals using Neuromorphic Energy-Efficient Temporal Neural Networks
• 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
• Low-Power Neuromorphic Hardware for Signal Processing Applications
• Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization
• A Neurally-Inspired Hierarchical Prediction Network for Spatiotemporal Sequence Learning and Prediction
• A Neural Spiking Approach Compared to Deep Feedforward Networks on Stepwise Pixel Erasement
• Improving STDP-based Visual Feature Learning with Whitening
• Spiking Neural Predictive Coding for Continual Learning from Data Streams
• Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks
• Algorithm and Hardware Design of Discrete-Time Spiking Neural Networks Based on Back Propagation with Binary Activations
• NatCSNN: A Convolutional Spiking Neural Network for recognition of objects extracted from natural images
• Exploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks
• Efficient Implementation of a Multi-Layer Gradient-Free Online-Trainable Spiking Neural Network on FPGA
• A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow
• Free-Space Optical Spiking Neural Network
• Reinforcement Learning with Feedback-modulated TD-STDP
• Implementing a foveal-pit inspired filter in a Spiking Convolutional Neural Network: a preliminary study
• Continuous Learning in a Single-Incremental-Task Scenario with Spike Features
• STCSNN: High energy efficiency spike-train level spiking neural networks with spatio-temporal conversion
• Tuning Convolutional Spiking Neural Network with Biologically-plausible Reward Propagation
• An All-Memristor Deep Spiking Neural Computing System: A Step Towards Realizing the Low Power,Stochastic Brain
• Shallow Unorganized Neural Networks using Smart Neuron Model for Visual Perception
• A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection
• ODMTCNet: An Interpretable Multi-view Deep Neural Network Architecture for Image Feature Representation
• Spiking Neural Networks with Single-Spike Temporal-Coded Neurons for Network Intrusion Detection
• Foveal-pit inspired filtering of DVS spike response
• A Microarchitecture Implementation Framework for Online Learning with Temporal Neural Networks
• Action Recognition Using Supervised Spiking Neural Networks
• Unsupervised Image Classification Through Time-Multiplexed Photonic Multi-Layer Spiking Convolutional Neural Network
• Unsupervised Spiking Instance Segmentation on Event Data using STDP
• The backpropagation-based recollection hypothesis: Backpropagated action potentials mediate recall, imagination, language understanding and naming
• BioLeaF: A Bio-plausible Learning Framework for Training of Spiking Neural Networks