Event-driven contrastive divergence for spiking neuromorphic systems,” Frontiers in neuroscience

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 advan-tages from the perspectives of scalability, power dissipa-tion and real-time interfacing with the environment. How-ever 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 sub-strate. Here, we present an event-driven variation of CD to train a RBM constructed with Integrate & Fire (I&F) neu-rons, 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 Boltz-mann distribution. The recurrent activity of the network re-places 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 com-∗Electronic address