Optimized hardware framework of MLP with random hidden layers for classification applications

Abdullah M. Zyarah; Abhishek Ramesh; Cory Merkel; Dhireesha Kudithipudi

doi:10.1117/12.2225498

12 May 2016 Optimized hardware framework of MLP with random hidden layers for classification applications

Abdullah M. Zyarah, Abhishek Ramesh, Cory Merkel, Dhireesha Kudithipudi

Proceedings Volume 9850, Machine Intelligence and Bio-inspired Computation: Theory and Applications X; 985007 (2016) https://doi.org/10.1117/12.2225498
Event: SPIE Defense + Security, 2016, Baltimore, MD, United States

Abstract

Multilayer Perceptron Networks with random hidden layers are very efficient at automatic feature extraction and offer significant performance improvements in the training process. They essentially employ large collection of fixed, random features, and are expedient for form-factor constrained embedded platforms. In this work, a reconfigurable and scalable architecture is proposed for the MLPs with random hidden layers with a customized building block based on CORDIC algorithm. The proposed architecture also exploits fixed point operations for area efficiency. The design is validated for classification on two different datasets. An accuracy of ~ 90% for MNIST dataset and 75% for gender classification on LFW dataset was observed. The hardware has 299 speed-up over the corresponding software realization.

Citation Download Citation

Abdullah M. Zyarah, Abhishek Ramesh, Cory Merkel, and Dhireesha Kudithipudi "Optimized hardware framework of MLP with random hidden layers for classification applications", Proc. SPIE 9850, Machine Intelligence and Bio-inspired Computation: Theory and Applications X, 985007 (12 May 2016); https://doi.org/10.1117/12.2225498

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available