Event-driven contrastive divergence for spiking neuromorphic systems

• Published in: Frontiers in neuroscience Vol. 7; p. 272
• Main Authors: Neftci, Emre, Das, Srinjoy, Pedroni, Bruno, Kreutz-Delgado, Kenneth, Cauwenberghs, Gert
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 30.01.2014; Frontiers Media S.A
• Subjects: Algorithms; Artificial intelligence; Dynamical systems; Fashion models; Firing pattern; Generative Model; Learning algorithms; Machine learning; Markov chain Monte Carlo; Neural networks; Neuromorphic Cognition; Neurons; Neuroscience; Neurosciences; Parameter estimation; Probability distribution; Random variables; recurrent neural network; synaptic plasticity; La Jolla California; United States > US; California; Markov chain monte carlo; neuromorphic cognition; recurrent neural network; generative model; synaptic plasticity
• ISSN: 1662-4548; 1662-453X; 1662-453X
• DOI: 10.3389/fnins.2013.00272

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.