Nikolaos Toulgaridis, Eleni Bougioukou and Theodore Antonakopoulos:

RBM-based Hardware Accelerator for Handwritten Digits Recognition

The 4th Panhellenic Conference on Electronics and Telecommunications, PACET-2017, Xanthi, 17-18 November 2017.

Abstract: Automatic recognition of handwritten digits is a well known application area of neural networks. Efficient implementation of neural networks is not a trivial task and various architectures have been proposed for that purpose. This work presents the architecture and implementation of a hardware accelerator for fast recognition of hand-written digits based on Restricted Boltzmann machines. Fixed and floating point arithmetic is used for minimizing the required hardware resources. The proposed architecture results to a processing rate of more than 10 Mimages/sec in a single FPGA board.

If you need additional information concerning this paper, please contact either one of the authors or send an e-mail to: comes-sup@ece.upatras.gr