Incremental Drain-Voltage-Ramping Training Method for Ferroelectric Field-Effect Transistor Synaptic Devices

Nguyen, Manh-Cuong; Lee, Kitae; Kim, Sihyun; Youn, Sangwook; Hwang, Yeongjin; Kim, Hyungjin; Choi, Rino; Kwon, Daewoong

doi:10.1109/led.2021.3127927

Cited by 19 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many works reported the ISPP scheme to mitigate nonlinear G responses in various FeFET-based synaptic devices. [30,31,[40][41][42] However, it is worth noting that generating incremental PGM pulses requires additional circuits and degrades the efficiency of neuromorphic systems. [44] From this perspective, the highly linear G response in the fabricated FeTFTs with the identical PGM pulses is a significant advantage in neuromorphic systems.…”

Section: Synaptic Characteristics Of the Fetftsmentioning

confidence: 99%

“…For example, incremental-step-pulse programming (ISPP) methods have been used to obtain linear conductance responses in FeFET-based synaptic devices. [30,31,[40][41][42] Iterative write-read-verify programming methods have also been widely used to address device variations. [43] However, these methods require additional circuitries and memory to generate programming pulses with different amplitudes or to read the conductance of the devices during the verification process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analog Synaptic Devices Based on IGZO Thin‐Film Transistors with a Metal–Ferroelectric–Metal–Insulator–Semiconductor Structure for High‐Performance Neuromorphic Systems

Kwon,

Park,

Shin

et al. 2023

Advanced Intelligent Systems

Self Cite

View full text Add to dashboard Cite

A ferroelectric thin‐film transistor (FeTFT)‐based synaptic device with an indium–gallium–zinc oxide (IGZO) channel and a metal–ferroelectric–metal–insulator–semiconductor (MFMIS) structure is reported. The fabricated FeTFT exhibits a highly linear conductance response (|α| = 0.21) with a large dynamic range (Gmax/Gmin ≈ 53.2), although identical program pulses are applied to the device. In addition, because the inner metal layer of the FeTFTs has an MFMIS structure, the electric field is uniformly applied to the entire IGZO channel, which reduces the cycle‐to‐cycle variation (σ = 0.47%) in the conductance responses. In the system simulation with the measured synaptic characteristics, the high classification accuracy of ≈97.0% is achieved in the MNIST image set, verifying the feasibility of FeTFT‐based neuromorphic systems.

show abstract

Section: Synaptic Characteristics Of the Fetftsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Analog Synaptic Devices Based on IGZO Thin‐Film Transistors with a Metal–Ferroelectric–Metal–Insulator–Semiconductor Structure for High‐Performance Neuromorphic Systems

Kwon,

Park,

Shin

et al. 2023

Advanced Intelligent Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…The most important components in such a system are artificial neurons and synapses. According to reported studies [94,[122][123][124][125][126][127][128][129][130][131][132][133][134][135], FeFETs can implement both artificial neurons and synapses. For applications in neurons, FeFETs functioning as pulsed neural networks have been commonly used in previous studies.…”

Section: Ferroelectric Devices For Neuromorphic Computingmentioning

confidence: 99%

“…From the results [129], it was concluded that the use of write pulses with suitable incremental voltage could help achieve excellent linearity and superior accuracy in neural network simulation. Furthermore, Nguyen et al implemented a writing method involving fixing the gate pulse while gradually increasing the drain pulse, and compared the differences to impose incremental gate pulses [130]. The effects of different ferroelectric structures [131] and working temperature [132] were also examined in the application of deep neural networks.…”

Section: Ferroelectric Devices For Neuromorphic Computingmentioning

confidence: 99%

Ferroelectric Devices for Intelligent Computing

et al. 2022

View full text Add to dashboard Cite

Recently, transistor scaling is approaching its physical limit, hindering the further development of the computing capability. In the post-Moore era, emerging logic and storage devices have been the fundamental hardware for expanding the capability of intelligent computing. In this article, the recent progress of ferroelectric devices for intelligent computing is reviewed. The material properties and electrical characteristics of ferroelectric devices are elucidated, followed by a discussion of novel ferroelectric materials and devices that can be used for intelligent computing. Ferroelectric capacitors, transistors, and tunneling junction devices used for low-power logic, high-performance memory, and neuromorphic applications are comprehensively reviewed and compared. In addition, to provide useful guidance for developing high-performance ferroelectric-based intelligent computing systems, the key challenges for realizing ultrascaled ferroelectric devices for high-efficiency computing are discussed.

show abstract

“…[21,22] Furthermore, prior studies were largely restricted to single-device-level inquiries. [23,24] It is critical, however, to examine how the characteristics of a single synaptic device are reflected throughout an entire neuromorphic system. Considering these two aspects, it is necessary to establish a method that enhances the durability of FeFETs and enables quantitative device-to-system-level characterization.…”

Section: Introductionmentioning

confidence: 99%

Self‐Curable Synaptic Ferroelectric FET Arrays for Neuromorphic Convolutional Neural Network

Shin

Koo

et al. 2023

Advanced Science

Self Cite

View full text Add to dashboard Cite

With the recently increasing prevalence of deep learning, both academia and industry exhibit substantial interest in neuromorphic computing, which mimics the functional and structural features of the human brain. To realize neuromorphic computing, an energy-efficient and reliable artificial synapse must be developed. In this study, the synaptic ferroelectric field-effect-transistor (FeFET) array is fabricated as a component of a neuromorphic convolutional neural network. Beyond the single transistor level, the long-term potentiation and depression of synaptic weights are achieved at the array level, and a successful program-inhibiting operation is demonstrated in the synaptic array, achieving a learning accuracy of 79.84% on the Canadian Institute for Advanced Research (CIFAR)-10 dataset. Furthermore, an efficient self-curing method is proposed to improve the endurance of the FeFET array by tenfold, utilizing the punch-through current inherent to the device. Low-frequency noise spectroscopy is employed to quantitatively evaluate the curing efficiency of the proposed self-curing method. The results of this study provide a method to fabricate and operate reliable synaptic FeFET arrays, thereby paving the way for further development of ferroelectric-based neuromorphic computing.

show abstract

Incremental Drain-Voltage-Ramping Training Method for Ferroelectric Field-Effect Transistor Synaptic Devices

Cited by 19 publications

References 23 publications

Analog Synaptic Devices Based on IGZO Thin‐Film Transistors with a Metal–Ferroelectric–Metal–Insulator–Semiconductor Structure for High‐Performance Neuromorphic Systems

Analog Synaptic Devices Based on IGZO Thin‐Film Transistors with a Metal–Ferroelectric–Metal–Insulator–Semiconductor Structure for High‐Performance Neuromorphic Systems

Ferroelectric Devices for Intelligent Computing

Self‐Curable Synaptic Ferroelectric FET Arrays for Neuromorphic Convolutional Neural Network

Contact Info

Product

Resources

About