GeCo: Classification Restricted Boltzmann Machine Hardware for On-chip Learning

Abstract

We present a Classification Restricted Boltzmann Machine (ClassRBM) hardware for embedded machines with on-chip learning capability. The RBM is a kind of the generative model, and has been used as one of the most popular feature extractors and image preprocessors. The ClassRBM is a variant of the RBM that is adapted to classification tasks. We propose the multi-Neuron-Per-Class (multi-NPC) voting scheme for improving accuracy of ClassRBM. We also show that the Contrastive Divergence (CD), which is one of the most popular algorithms to train RBM, has limitations in multi-NPC ClassRBM learning and propose a modified CD algorithm to overcome the limitation. Experimental results on FPGA flatform for MNIST datasets confirm that classification accuracy of the proposed algorithm is∼ 2.12% higher than the conventional CD.