Header

UZH-Logo

Maintenance Infos

Analog Weight Updates with Compliance Current Modulation of Binary ReRAMs for On-Chip Learning


Payvand, Melika; Demirag, Yigit; Dalgaty, Thomas; Vianello, Elisa; Indiveri, Giacomo (2020). Analog Weight Updates with Compliance Current Modulation of Binary ReRAMs for On-Chip Learning. In: 2020 IEEE International Symposium on Circuits and Systems (ISCAS), Seville, Spain, 10 October 2020 - 21 October 2020, IEEE.

Abstract

Many edge computing and IoT applications require adaptive and on-line learning architectures for fast and low-power processing of locally sensed signals. A promising class of architectures to solve this problem is that of in-memory computing ones, based on event-based hybrid memristive-CMOS devices. In this work, we present an example of such systems that supports always-on on-line learning. To overcome the problems of variability and limited resolution of ReRAM memristive devices used to store synaptic weights, we propose to use only their High Conductive State (HCS) and control their desired conductance by modulating their programming Compliance Current (I CC ). We describe the spike-based learning CMOS circuits that are used to modulate the synaptic weights and demonstrate the relationship between the synaptic weight, the device conductance, and the I CC used to set its weight, with experimental measurements from a 4kb array of HfO 2 -based devices. To validate the approach and the circuits presented, we present circuit simulation results for a standard CMOS 180nm process and system-level behavioral simulations for classifying hand-written digits from the MNIST data-set with classification accuracy of 92.68% on the test set.

Abstract

Many edge computing and IoT applications require adaptive and on-line learning architectures for fast and low-power processing of locally sensed signals. A promising class of architectures to solve this problem is that of in-memory computing ones, based on event-based hybrid memristive-CMOS devices. In this work, we present an example of such systems that supports always-on on-line learning. To overcome the problems of variability and limited resolution of ReRAM memristive devices used to store synaptic weights, we propose to use only their High Conductive State (HCS) and control their desired conductance by modulating their programming Compliance Current (I CC ). We describe the spike-based learning CMOS circuits that are used to modulate the synaptic weights and demonstrate the relationship between the synaptic weight, the device conductance, and the I CC used to set its weight, with experimental measurements from a 4kb array of HfO 2 -based devices. To validate the approach and the circuits presented, we present circuit simulation results for a standard CMOS 180nm process and system-level behavioral simulations for classifying hand-written digits from the MNIST data-set with classification accuracy of 92.68% on the test set.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

109 downloads since deposited on 16 Feb 2021
31 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:21 October 2020
Deposited On:16 Feb 2021 08:22
Last Modified:27 Jan 2022 05:54
Publisher:IEEE
ISBN:9781728133201
OA Status:Green
Publisher DOI:https://doi.org/10.1109/iscas45731.2020.9180808
  • Content: Accepted Version