Voltage-mode reservoir computing with ferroelectric CMOS inverters

We propose reservoir computing (RC) utilizing a CMOS inverter composed of ferroelectric FETs (FeCMOS) to enhance energy efficiency and computational capability. We confirmed that the output voltage of an FeCMOS exhibits hysteresis characteristics originating from ferroelectric polarization dynamics...

Full description

Saved in:
Bibliographic Details
Main Authors: Rikuo Suzuki, Kasidit Toprasertpong, Ryosho Nakane, Eishin Nako, Mitsuru Takenaka, Shinichi Takagi
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Applied Physics Express
Subjects:
Online Access:https://doi.org/10.35848/1882-0786/ade199
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849424192617840640
author Rikuo Suzuki
Kasidit Toprasertpong
Ryosho Nakane
Eishin Nako
Mitsuru Takenaka
Shinichi Takagi
author_facet Rikuo Suzuki
Kasidit Toprasertpong
Ryosho Nakane
Eishin Nako
Mitsuru Takenaka
Shinichi Takagi
author_sort Rikuo Suzuki
collection DOAJ
description We propose reservoir computing (RC) utilizing a CMOS inverter composed of ferroelectric FETs (FeCMOS) to enhance energy efficiency and computational capability. We confirmed that the output voltage of an FeCMOS exhibits hysteresis characteristics originating from ferroelectric polarization dynamics and the FeCMOS RC has the capability to solve fundamental nonlinear problems. Furthermore, we introduced a technique to enhance the computational capability of FeCMOS RC by adjusting the center of the operating voltage according to the threshold voltage. This approach facilitates transient dynamics with a wider range of intermediate output voltage and enhances the performance of the RC system. We also demonstrate that FeCMOS RC can solve nonlinear time-series prediction tasks with higher energy efficiency than conventional FeFET RC systems.
format Article
id doaj-art-6a73708d6f254ed39cfee28b0e867096
institution Kabale University
issn 1882-0786
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Applied Physics Express
spelling doaj-art-6a73708d6f254ed39cfee28b0e8670962025-08-20T03:30:19ZengIOP PublishingApplied Physics Express1882-07862025-01-0118606100210.35848/1882-0786/ade199Voltage-mode reservoir computing with ferroelectric CMOS invertersRikuo Suzuki0https://orcid.org/0009-0002-1952-3509Kasidit Toprasertpong1https://orcid.org/0000-0003-4206-8698Ryosho Nakane2https://orcid.org/0000-0002-9059-9349Eishin Nako3Mitsuru Takenaka4https://orcid.org/0000-0002-9852-1474Shinichi Takagi5https://orcid.org/0000-0002-5601-2604Department of Electrical Engineering and Information Systems, The University of Tokyo , 7-3-1 Hongo, Bunkyo, Tokyo 113-8656, JapanDepartment of Electrical Engineering and Information Systems, The University of Tokyo , 7-3-1 Hongo, Bunkyo, Tokyo 113-8656, JapanDepartment of Electrical Engineering and Information Systems, The University of Tokyo , 7-3-1 Hongo, Bunkyo, Tokyo 113-8656, JapanDepartment of Electrical Engineering and Information Systems, The University of Tokyo , 7-3-1 Hongo, Bunkyo, Tokyo 113-8656, JapanDepartment of Electrical Engineering and Information Systems, The University of Tokyo , 7-3-1 Hongo, Bunkyo, Tokyo 113-8656, JapanDepartment of Electrical Engineering and Information Systems, The University of Tokyo , 7-3-1 Hongo, Bunkyo, Tokyo 113-8656, JapanWe propose reservoir computing (RC) utilizing a CMOS inverter composed of ferroelectric FETs (FeCMOS) to enhance energy efficiency and computational capability. We confirmed that the output voltage of an FeCMOS exhibits hysteresis characteristics originating from ferroelectric polarization dynamics and the FeCMOS RC has the capability to solve fundamental nonlinear problems. Furthermore, we introduced a technique to enhance the computational capability of FeCMOS RC by adjusting the center of the operating voltage according to the threshold voltage. This approach facilitates transient dynamics with a wider range of intermediate output voltage and enhances the performance of the RC system. We also demonstrate that FeCMOS RC can solve nonlinear time-series prediction tasks with higher energy efficiency than conventional FeFET RC systems.https://doi.org/10.35848/1882-0786/ade199reservoir computingferroelectric FETedge AICMOS technologytime-series predictionenergy efficiency
spellingShingle Rikuo Suzuki
Kasidit Toprasertpong
Ryosho Nakane
Eishin Nako
Mitsuru Takenaka
Shinichi Takagi
Voltage-mode reservoir computing with ferroelectric CMOS inverters
Applied Physics Express
reservoir computing
ferroelectric FET
edge AI
CMOS technology
time-series prediction
energy efficiency
title Voltage-mode reservoir computing with ferroelectric CMOS inverters
title_full Voltage-mode reservoir computing with ferroelectric CMOS inverters
title_fullStr Voltage-mode reservoir computing with ferroelectric CMOS inverters
title_full_unstemmed Voltage-mode reservoir computing with ferroelectric CMOS inverters
title_short Voltage-mode reservoir computing with ferroelectric CMOS inverters
title_sort voltage mode reservoir computing with ferroelectric cmos inverters
topic reservoir computing
ferroelectric FET
edge AI
CMOS technology
time-series prediction
energy efficiency
url https://doi.org/10.35848/1882-0786/ade199
work_keys_str_mv AT rikuosuzuki voltagemodereservoircomputingwithferroelectriccmosinverters
AT kasidittoprasertpong voltagemodereservoircomputingwithferroelectriccmosinverters
AT ryoshonakane voltagemodereservoircomputingwithferroelectriccmosinverters
AT eishinnako voltagemodereservoircomputingwithferroelectriccmosinverters
AT mitsurutakenaka voltagemodereservoircomputingwithferroelectriccmosinverters
AT shinichitakagi voltagemodereservoircomputingwithferroelectriccmosinverters