In‐Memory Binary Vector–Matrix Multiplication Based on Complementary Resistive Switches

Advanced Intelligent Systems, vol. 2

Abstract

Binary Neural Networks In article number 2000134, Stephan Menzel and co-workers explore a computation in-memory concept for binary vector-matrix multiplications based on complementary resistive switches. Experimental results on a small-scale demonstrator are shown and the influence of device variability is investigated. The simulated inference of a 1-layer fully connected binary neural network trained on the MNIST data set resulted in an accuracy of nearly 86%.

Authors 4

1. Tobias Ziegler Aachen JARA-FIT Institute of Materials in Electrical Engineering and Information Technology II

   RWTH Aachen University · Jülich Aachen Research Alliance

   Affiliation as printed

   JARA-FIT and Institute of Materials in Electrical Engineering and Information Technology II RWTH Aachen University Sommerfeldstraße 24 Aachen 52074 Germany

2. Rainer Waser Aachen JARA-FIT Institute of Materials in Electrical Engineering and Information Technology II

   RWTH Aachen University · Forschungszentrum Jülich · Jülich Aachen Research Alliance

   Affiliation as printed

   JARA-FIT and Institute of Materials in Electrical Engineering and Information Technology II RWTH Aachen University Sommerfeldstraße 24 Aachen 52074 Germany

   JARA-FIT and Peter Grünberg Institute 10 Forschungszentrum Jülich GmbH Wilhelm-Johnen-Straße Jülich 52428 Germany

   JARA-FIT and Peter Grünberg Institute 7 Forschungszentrum Jülich GmbH Wilhelm-Johnen-Straße Jülich 52428 Germany

3. Dirk J. Wouters Aachen JARA-FIT Institute of Materials in Electrical Engineering and Information Technology II

   RWTH Aachen University · Jülich Aachen Research Alliance

   Affiliation as printed

   JARA-FIT and Institute of Materials in Electrical Engineering and Information Technology II RWTH Aachen University Sommerfeldstraße 24 Aachen 52074 Germany

4. Stephan Menzel corresponding

   Forschungszentrum Jülich · Jülich Aachen Research Alliance

   Affiliation as printed

   JARA-FIT and Peter Grünberg Institute 7 Forschungszentrum Jülich GmbH Wilhelm-Johnen-Straße Jülich 52428 Germany