Inherent Stochastic Learning in CMOS-Integrated HfO2 Arrays for Neuromorphic Computing

Based on the inherent stochasticity of CMOS-integrated HfO 2 -based resistive random access memory (RRAM) devices, a new learning algorithm for neuro-morphic systems is presented. For this purpose, the device-to-device variability of CMOS-integrated 4-kbit 1T-1R arrays is examined. To demonstrate th...

Full description

Saved in:
Bibliographic Details
Published in:IEEE electron device letters 2019-04, Vol.40 (4), p.639-642
Main Authors: Wenger, C., Zahari, F., Mahadevaiah, M. K., Perez, E., Beckers, I., Kohlstedt, H., Ziegler, M.
Format: Article
Language:English
Subjects:
Algorithms
CMOS
Gaussian distribution
Hafnium compounds
Hafnium oxide
HfO
Machine learning
Memory devices
neuro-morphic computing
Neuromorphics
Neurons
Object recognition
Pattern recognition
Performance evaluation
Random access memory
RRAM
Switches
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Based on the inherent stochasticity of CMOS-integrated HfO 2 -based resistive random access memory (RRAM) devices, a new learning algorithm for neuro-morphic systems is presented. For this purpose, the device-to-device variability of CMOS-integrated 4-kbit 1T-1R arrays is examined. To demonstrate the performance of the stochastic learning algorithm and the potential of RRAM technologies for neuro-morphic systems, a two-layer mixed-signal neural circuit for pattern recognition is implemented and tested with MNIST data.
ISSN:0741-3106
1558-0563
DOI:10.1109/LED.2019.2900867