4.8 Article

CMOS-compatible compute-in-memory accelerators based on integrated ferroelectric synaptic arrays for convolution neural networks

Related references

Note: Only part of the references are listed.
Article Chemistry, Multidisciplinary

Wafer-Scale 2D Hafnium Diselenide Based Memristor Crossbar Array for Energy-Efficient Neural Network Hardware

Sifan Li et al.

Summary: The study demonstrates a memristor crossbar array using large-scale hafnium diselenide thin films and a metal-assisted transfer technique, showing low switching voltage and energy, high recognition accuracy, and power efficiency. Hardware multiply-and-accumulate operation and programmable kernel-based image processing were successfully showcased.

ADVANCED MATERIALS (2022)

Article Physics, Applied

Oxide semiconductor-based ferroelectric thin-film transistors for advanced neuromorphic computing

Min-Kyu Kim et al.

Summary: A ferroelectric thin-film transistor (FeTFT) utilizing zirconium-doped hafnia and indium zinc tin oxide has been proposed for neuromorphic computing applications, showing reliable conductance modulation characteristics suitable for both deep neural networks and spiking neural networks. The FeTFT demonstrated high recognition accuracy for hand-written images and ability to emulate spike-time-dependent plasticity, indicating its promise as a candidate for neuromorphic computing hardware.

APPLIED PHYSICS LETTERS (2021)

Article Mathematics, Interdisciplinary Applications

Multilevel switching memristor by compliance current adjustment for off-chip training of neuromorphic system

Tae-Hyeon Kim et al.

Summary: This study explored the feasibility of achieving a larger number of conductance states using the I-cc control method, with experimental results demonstrating 64-level conductance states. Through off-chip learning of the CNN structure, it was verified that the 64-level states showed recognition performance close to that of software-based neural networks. By reducing information loss in the transfer process, the fabricated synaptic device array with the I-cc control programming method is expected to contribute to the development of hardware neural networks.

CHAOS SOLITONS & FRACTALS (2021)

Article Physics, Applied

Li memristor-based MOSFET synapse for linear I-V characteristic and processing analog input neuromorphic system

Chuljun Lee et al.

Summary: The research proposed a method to improve the linearity of current-voltage characteristics of synapse devices, utilizing a combination of MOSFET and Li-ion memristor to achieve gradual channel conductance changes for analog synaptic weights. This led to a significantly improved accuracy in recognizing the MNIST dataset.

JAPANESE JOURNAL OF APPLIED PHYSICS (2021)

Article Multidisciplinary Sciences

Parallel convolutional processing using an integrated photonic tensor core

J. Feldmann et al.

Summary: With the advancement of technology, the demand for fast processing of large amounts of data is increasing, making highly parallelized, fast, and scalable hardware crucial. The integration of photonics can serve as the optical analogue of an application-specific integrated circuit, enabling photonic in-memory computing and efficient computational hardware.

NATURE (2021)

Article Computer Science, Hardware & Architecture

DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-Chip Training

Xiaochen Peng et al.

Summary: DNN+NeuroSim is an integrated framework for benchmarking compute-in-memory (CIM) accelerators for deep neural networks. It automatically maps algorithms to hardware, evaluates chip-level metrics, and investigates the impact of analog nonvolatile memory (eNVM) device properties on on-chip training. This framework provides insights into synaptic devices for on-chip training and is available for both inference and training versions on GitHub.

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS (2021)

Article Multidisciplinary Sciences

CMOS-compatible ferroelectric NAND flash memory for high-density, low-power, and high-speed three-dimensional memory

Min-Kyu Kim et al.

Summary: Ferroelectric memory has been extensively researched for its potential of higher speed, lower power consumption, and longer endurance compared to conventional flash memory. By utilizing hafnia-based ferroelectrics and oxide semiconductors, it is possible to avoid unwanted interfacial layers and achieve unprecedented Si-free 3D integration of ferroelectric memory, with memory performance surpassing conventional flash memory and previous perovskite ferroelectric memories.

SCIENCE ADVANCES (2021)

Article Engineering, Electrical & Electronic

Multinary Data Processing Based on Nonlinear Synaptic Devices

Myungjun Kim et al.

Summary: The study demonstrated the use of stasis weight for multinary data processing in a neuromorphic system, and proposed pulse modulation circuits to improve inference accuracy through pulse amplitude transformation. This led to a significant improvement in the accuracy of the simulated MNIST dataset.

JOURNAL OF ELECTRONIC MATERIALS (2021)

Review Physics, Applied

Domains and domain dynamics in fluorite-structured ferroelectrics

Dong Hyun Lee et al.

Summary: Fluorite-structured ferroelectrics like HfO2 and ZrO2 have garnered increasing interest since 2011 for their potential in semiconductor devices and high-density information storage. Research on these materials has focused on understanding their ferroelectric properties and enhancing device performance to meet the requirements for high operating speed, reliability, and multilevel data storage.

APPLIED PHYSICS REVIEWS (2021)

Article Multidisciplinary Sciences

Fully hardware-implemented memristor convolutional neural network

Peng Yao et al.

NATURE (2020)

Article Multidisciplinary Sciences

Accurate deep neural network inference using computational phase-change memory

Vinay Joshi et al.

NATURE COMMUNICATIONS (2020)

Article Multidisciplinary Sciences

Enhanced ferroelectricity in ultrathin films grown directly on silicon

Suraj S. Cheema et al.

NATURE (2020)

Review Nanoscience & Nanotechnology

Memory devices and applications for in-memory computing

Abu Sebastian et al.

NATURE NANOTECHNOLOGY (2020)

Review Engineering, Electrical & Electronic

Neuro-inspired computing chips

Wenqiang Zhang et al.

NATURE ELECTRONICS (2020)

Article Nanoscience & Nanotechnology

Alloying conducting channels for reliable neuromorphic computing

Hanwool Yeon et al.

NATURE NANOTECHNOLOGY (2020)

Article Multidisciplinary Sciences

Scale-free ferroelectricity induced by flat phonon bands in HfO2

Hyun-Jae Lee et al.

SCIENCE (2020)

Article Multidisciplinary Sciences

Optogenetics inspired transition metal dichalcogenide neuristors for in-memory deep recurrent neural networks

Rohit Abraham John et al.

NATURE COMMUNICATIONS (2020)

Article Materials Science, Multidisciplinary

Ferroelectric devices and circuits for neuro-inspired computing

Panni Wang et al.

MRS COMMUNICATIONS (2020)

Article Engineering, Electrical & Electronic

The future of ferroelectric field-effect transistor technology

Asif Islam Khan et al.

NATURE ELECTRONICS (2020)

Review Multidisciplinary Sciences

Emerging Materials for Neuromorphic Devices and Systems

Min-Kyu Kim et al.

ISCIENCE (2020)

Review Chemistry, Multidisciplinary

Neuromorphic Engineering: From Biological to Spike-Based Hardware Nervous Systems

Jia-Qin Yang et al.

ADVANCED MATERIALS (2020)

Article Engineering, Electrical & Electronic

Controlling the Neuromorphic Behavior of Organic Electrochemical Transistors by Blending Mixed and Ion Conductors

Shunsuke Yamamoto et al.

ACS APPLIED ELECTRONIC MATERIALS (2020)

Review Chemistry, Multidisciplinary

Research progress on solutions to the sneak path issue in memristor crossbar arrays

Lingyun Shi et al.

NANOSCALE ADVANCES (2020)

Review Materials Science, Multidisciplinary

Emerging memory devices for artificial synapses

Youngjun Park et al.

JOURNAL OF MATERIALS CHEMISTRY C (2020)

Article Engineering, Electrical & Electronic

Three-dimensional memristor circuits as complex neural networks

Peng Lin et al.

NATURE ELECTRONICS (2020)

Review Engineering, Electrical & Electronic

Recent Progress in Artificial Synapses Based on Two-Dimensional van der Waals Materials for Brain-Inspired Computing

Seunghwan Seo et al.

ACS APPLIED ELECTRONIC MATERIALS (2020)

Article Chemistry, Multidisciplinary

Ferroelectric Analog Synaptic Transistors

Min-Kyu Kim et al.

NANO LETTERS (2019)

Review Materials Science, Multidisciplinary

Emerging Artificial Synaptic Devices for Neuromorphic Computing

Qingzhou Wan et al.

ADVANCED MATERIALS TECHNOLOGIES (2019)

Article Chemistry, Multidisciplinary

Recent Progress in Three-Terminal Artificial Synapses: From Device to System

Hong Han et al.

SMALL (2019)

Article Computer Science, Information Systems

A TaOx-Based Electronic Synapse With High Precision for Neuromorphic Computing

Sen Liu et al.

IEEE ACCESS (2019)

Article Chemistry, Multidisciplinary

Memristor-Based Analog Computation and Neural Network Classification with a Dot Product Engine

Miao Hu et al.

ADVANCED MATERIALS (2018)

Article Computer Science, Hardware & Architecture

NeuroSim: A Circuit-Level Macro Model for Benchmarking Neuro-Inspired Architectures in Online Learning

Pai-Yu Chen et al.

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS (2018)

Article Engineering, Electrical & Electronic

Neuro-Inspired Computing With Emerging Nonvolatile Memory

Shimeng Yu

PROCEEDINGS OF THE IEEE (2018)

Article Multidisciplinary Sciences

Efficient and self-adaptive in-situ learning in multilayer memristor neural networks

Can Li et al.

NATURE COMMUNICATIONS (2018)

Article Engineering, Electrical & Electronic

Write Disturb in Ferroelectric FETs and Its Implication for 1T-FeFET AND Memory Arrays

Kai Ni et al.

IEEE ELECTRON DEVICE LETTERS (2018)

Article Engineering, Electrical & Electronic

Switching Dynamics of Ferroelectric Zr-Doped HfO2

Cristobal Alessandri et al.

IEEE ELECTRON DEVICE LETTERS (2018)

Article Engineering, Electrical & Electronic

Implementation of Convolutional Kernel Function Using 3-D TiOx Resistive Switching Devices for Image Processing

Myonghoon Kwak et al.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2018)

Article Physics, Applied

A ferroelectric field effect transistor based synaptic weight cell

Matthew Jerry et al.

JOURNAL OF PHYSICS D-APPLIED PHYSICS (2018)

Review Engineering, Electrical & Electronic

Organic electronics for neuromorphic computing

Yoeri van De Burgt et al.

NATURE ELECTRONICS (2018)

Review Engineering, Electrical & Electronic

Scaling for edge inference of deep neural networks

Xiaowei Xu et al.

NATURE ELECTRONICS (2018)

Article Engineering, Electrical & Electronic

Analogue signal and image processing with large memristor crossbars

Can Li et al.

NATURE ELECTRONICS (2018)

Article Chemistry, Multidisciplinary

Li-Ion Synaptic Transistor for Low Power Analog Computing

Elliot J. Fuller et al.

ADVANCED MATERIALS (2017)

Article Multidisciplinary Sciences

Neuromorphic device architectures with global connectivity through electrolyte gating

Paschalis Gkoupidenis et al.

NATURE COMMUNICATIONS (2017)

Article Engineering, Electrical & Electronic

Demonstration of Convolution Kernel Operation on Resistive Cross-Point Array

Ligang Gao et al.

IEEE ELECTRON DEVICE LETTERS (2016)

Article Engineering, Electrical & Electronic

Demonstration of Low Power 3-bit Multilevel Cell Characteristics in a TaOx-Based RRAM by Stack Engineering

Amit Prakash et al.

IEEE ELECTRON DEVICE LETTERS (2015)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Physics, Applied

64 kbit Ferroelectric-Gate-Transistor-Integrated NAND Flash Memory with 7.5 V Program and Long Data Retention

Xizhen Zhang et al.

JAPANESE JOURNAL OF APPLIED PHYSICS (2013)