Share Email Print
cover

Proceedings Paper

Heterogeneous CMOS/memristor hardware neural networks for real-time target classification
Author(s): Cory Merkel; Dhireesha Kudithipudi; Ray Ptucha
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The advent of nanoscale metal-insulator-metal (MIM) structures with memristive properties has given birth to a new generation of hardware neural networks based on CMOS/memristor integration (CMHNNs). The advantage of the CMHNN paradigm compared to a pure CMOS approach lies in the multi-faceted functionality of memristive devices: They can efficiently store neural network configurations (weights and activation function parameters) via non-volatile, quasi-analog resistance states. They also provide high-density interconnects between neurons when integrated into 2-D and 3-D crossbar architectures. In this work, we explore the combination of CMHNN classifiers with manifold learning to reduce the dimensionality of CMHNN inputs. This allows the size of the CMHNN to be reduced significantly (by ≈ 97%). We tested the proposed system using the Caltech101 database and were able to achieve classification accuracies within ≈ 1:5% of those produced by a traditional support vector machine.

Paper Details

Date Published: 22 May 2014
PDF: 10 pages
Proc. SPIE 9119, Machine Intelligence and Bio-inspired Computation: Theory and Applications VIII, 911908 (22 May 2014); doi: 10.1117/12.2053436
Show Author Affiliations
Cory Merkel, Rochester Institute of Technology (United States)
Dhireesha Kudithipudi, Rochester Institute of Technology (United States)
Ray Ptucha, Rochester Institute of Technology (United States)


Published in SPIE Proceedings Vol. 9119:
Machine Intelligence and Bio-inspired Computation: Theory and Applications VIII
Misty Blowers; Jonathan Williams, Editor(s)

© SPIE. Terms of Use
Back to Top