Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems

Abstract

Restricted Boltzmann Machines (RBMs) and Deep Belief Networks have been demonstrated to perform efficiently in a variety of applications, such as dimensionality reduction, feature learning, and classification. Their implementation on neuromorphic hardware platforms emulating large-scale networks of spiking neurons can have significant advantages from the perspectives of scalability, power dissipation and real-time interfacing with the environment. However the traditional RBM architecture and the commonly used training algorithm known as Contrastive Divergence (CD) are based on discrete updates and exact arithmetics which do not directly map onto a dynamical neural substrate. Here, we present an event-driven variation of CD to train a RBM constructed with Integrate & Fire (I&F) neurons, that is constrained by the limitations of existing and near future neuromorphic hardware platforms. Our strategy is based on neural sampling, which allows us to synthesize a spiking neural network that samples from a target Boltzmann distribution. The recurrent activity of the network replaces the discrete steps of the CD algorithm, while Spike Time Dependent Plasticity (STDP) carries out the weight updates in an online, asynchronous fashion. We demonstrate our approach by training an RBM composed of leaky I&F neurons with STDP synapses to learn a generative model of the MNIST hand-written digit dataset, and by testing it in recognition, generation and cue integration tasks. Our results contribute to a machine learning-driven approach for synthesizing networks of spiking neurons capable of carrying out practical, high-level functionality.

(Under review)

References in corpus (3)

• Building high-level features using large scale unsupervised learning
• Stochastic inference with deterministic spiking neurons
• The thermodynamic temperature of a rhythmic spiking network

Cited by in corpus (32)

• Deep Learning in Neural Networks: An Overview
• Deep Learning in Spiking Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• Neuromorphic electronic circuits for building autonomous cognitive systems
• Neuromorphic Deep Learning Machines
• Spiking Deep Networks with LIF Neurons
• First-spike based visual categorization using reward-modulated STDP
• Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
• Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing
• Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines
• Biologically plausible deep learning -- but how far can we go with shallow networks?
• Training Spiking Deep Networks for Neuromorphic Hardware
• Stochastic inference with spiking neurons in the high-conductance state
• Bio-Inspired Spiking Convolutional Neural Network using Layer-wise Sparse Coding and STDP Learning
• Training a Probabilistic Graphical Model with Resistive Switching Electronic Synapses
• Efficient Spiking Neural Networks with Logarithmic Temporal Coding
• An optimised deep spiking neural network architecture without gradients
• Fast and energy-efficient neuromorphic deep learning with first-spike times
• SpikE: spike-based embeddings for multi-relational graph data
• VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner-Take-All Circuits
• The Discrete Langevin Machine: Bridging the Gap Between Thermodynamic and Neuromorphic Systems
• Spiking Neural Predictive Coding for Continual Learning from Data Streams
• An energy-based model for neuro-symbolic reasoning on knowledge graphs
• Spike-based computation using classical recurrent neural networks
• Event-based update of synapses in voltage-based learning rules
• evt_MNIST: A spike based version of traditional MNIST
• Gibbs Sampling with Low-Power Spiking Digital Neurons
• Supervised Training of Siamese Spiking Neural Networks with Earth Mover's Distance
• Ultra-low power on-chip learning of speech commands with phase-change memories
• Inherent Weight Normalization in Stochastic Neural Networks
• Opportunities for Analog Coding in Emerging Memory Systems
• Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning