☆ 4.6 Article

Hardware-Based Ternary Neural Network Using AND-Type Poly-Si TFT Array and Its Optimization Guideline

IEEE TRANSACTIONS ON ELECTRON DEVICES (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Electrical & Electronic

Cointegration of the TFT-Type AND Flash Synaptic Array and CMOS Circuits for a Hardware-Based Neural Network

Min-Kyu Park et al.

Summary: This study proposes and verifies a novel method of integrating an AND-type flash synaptic array with CMOS circuits. By reducing the number of masks and fabrication steps, the proposed method successfully integrates the synaptic array and CMOS peripheral circuits on a single wafer. This research is of great significance for the efficient implementation of hardware-based neural networks.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2023)

Add to Collection

Article Physics, Applied

Super-steep synapses based on positive feedback devices for reliable binary neural networks

Dongseok Kwon et al.

Summary: This work proposes positive feedback (PF) device-based synaptic devices for reliable binary neural networks (BNNs). The fabricated PF device shows a high on/off current ratio (2.69 x 10(7)) due to PF operation. The PF device has a charge-trap layer for adjusting the turn-on voltage (V-on) through program/erase operations and implementing long-term memory function. The steep switching characteristics of the PF device provide tolerance to retention time and turn-on voltage variation, enabling high accuracy (88.44% for CIFAR-10 image classification) in hardware-based BNNs using PF devices as synapses.

APPLIED PHYSICS LETTERS (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Capacitor-Based Synaptic Devices for Hardware Spiking Neural Networks

Sungmin Hwang et al.

Summary: This work presents a hardware neural network using capacitor-based synaptic devices. A MOS capacitor structure with a charge trapping layer was developed for the capacitor-based synaptic device. By using the charge occurring during the capacitor's charging and discharging process, multilevel weight values can be implemented. The vector-matrix multiplication (VMM) function was also experimentally verified using a fabricated synapse array based on NAND flash structure.

IEEE ELECTRON DEVICE LETTERS (2022)

Add to Collection

Review Engineering, Electrical & Electronic

Review of Analog Neuron Devices for Hardware-based Spiking Neural Networks

Dongseok Kwon et al.

Summary: In order to process data operations more efficiently in deep neural networks, researchers have been studying spiking neural networks. CMOS neuron circuits that mimic the biological behavior of neurons have been the main focus in the reported literature. However, conventional neuronal circuits need improvement in terms of area and energy consumption, leading to the emergence of neuron devices with memory functions. In this review article, neuron devices that can increase integration density and reduce power consumption in conventional neuronal circuits are discussed, and their potential importance in future neuromorphic systems is emphasized.

JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE (2022)

Add to Collection

Article Multidisciplinary Sciences

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

Min-Kyu Kim et al.

Summary: In this study, integrated ferroelectric thin-film transistor (FeTFT) synaptic arrays were demonstrated to provide efficient parallel programming and data processing for CNNs through selective and accurate control of polarization in the ferroelectric layer.

SCIENCE ADVANCES (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Highly Linear Analog Spike Processing Block Integrated With an AND-Type Flash Array and CMOS Neuron Circuits

Kyu-Ho Lee et al.

Summary: In this article, a highly linear spike processing block (SPB) integrating AND-type charge-trap flash (CTF) synapse array and CMOS integrate-and-fire (IF) neurons is fabricated for hardware-based spiking neural networks (SNNs). The SPB exhibits a highly linear relationship between the current sum and the output spike frequency, enabling precise mimicry of artificial neural networks with ReLU activation function. A single layer SNN is experimentally demonstrated for classifying digit patterns.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Ferroelectric Field-Effect Transistors for Binary Neural Network With 3-D NAND Architecture

Geun Ho Lee et al.

Summary: FeFET, as a nonvolatile memory device, can be used as a synaptic device in neuromorphic systems. Utilizing HZO material and the 3-D nand structure, it has been verified and simulated, with a proposed method to increase synaptic cell efficiency.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2022)

Add to Collection

Article Engineering, Electrical & Electronic

A 40-nm MLC-RRAM Compute-in-Memory Macro With Sparsity Control, On-Chip Write-Verify, and Temperature-Independent ADC References

Wantong Li et al.

Summary: RRAM-based compute-in-memory (CIM) shows great potential for accelerating DNN inference, but device characteristics and off-chip techniques may limit its capabilities. This work presents an RRAM-CIM macro design that features multi-level cell (MLC) RRAM, sparsity-aware input control, on-chip write-verify, and on-chip ADC reference generation.

IEEE JOURNAL OF SOLID-STATE CIRCUITS (2022)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic

An Analog In-Memory-Search Solution based on 3D-NAND Flash Memory for Brain-Inspired Computing

Po-Hao Tseng et al.

Summary: This study presents a high-performance AIMS chip based on 3D-NAND flash, which enables novel searching/matching functionality in the analog domain. With analog range storage and gradient range boundary, the chip achieves excellent inference accuracy in face recognition.

2022 INTERNATIONAL ELECTRON DEVICES MEETING, IEDM (2022)

Add to Collection

Article Automation & Control Systems

4-bit Multilevel Operation in Overshoot Suppressed Al2O3/TiOx Resistive Random-Access Memory Crossbar Array

Sungjoon Kim et al.

Summary: By introducing and optimizing an overshoot suppression layer, the shortcomings in the forming stage of filamentary RRAMs are overcome, enabling gradual switching characteristics in both set and reset regions and implementation of 4-bit multilevel operation. The forming step can be easily performed in a 16 x 16 crossbar array with self-compliance characteristics without disturbing neighboring cells.

ADVANCED INTELLIGENT SYSTEMS (2022)

Add to Collection

Article Chemistry, Analytical

Efficient fusion of spiking neural networks and FET-type gas sensors for a fast and reliable artificial olfactory system

Dongseok Kwon et al.

Summary: A new artificial olfactory system based on a spiking neural network (SNN) and field-effect transistor (FET)-type gas sensors was proposed for quickly and reliably detecting toxic gases. The system showed a low error rate in predicting the concentrations of NO2 and H2S, with real-time gas concentration prediction achieved within approximately 5 seconds. The hardware-based SNN outperformed conventional machine learning algorithms, showcasing its superiority in detecting toxic gases.

SENSORS AND ACTUATORS B-CHEMICAL (2021)

Add to Collection

Article Engineering, Electrical & Electronic

3-D AND-Type Flash Memory Architecture With High-κ Gate Dielectric for High-Density Synaptic Devices

Young-Tak Seo et al.

Summary: This paper introduces a novel 3-D synaptic device structure with features of high-speed operation, high density, and stacking layers, and successfully verifies its potential application in neuromorphic networks. Additionally, hardware-based CNN design and accuracy evaluation of CIFAR-10 image classification are demonstrated.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2021)

Add to Collection

Article Multidisciplinary Sciences

4K-memristor analog-grade passive crossbar circuit

H. Kim et al.

Summary: The superior density of passive analog-grade memristive crossbar circuits allows for storing large neural network models on specialized neuromorphic chips to avoid costly off-chip communication. A 64x64 passive crossbar circuit with high functional nonvolatile metal-oxide memristors was successfully fabricated with low variation in memristor switching voltages. Experimental verification of analog properties demonstrated accurate modeling for MNIST image classification and large-scale multilayer perceptron classifier based on advanced conductance tuning algorithm.

NATURE COMMUNICATIONS (2021)

Add to Collection

Article Computer Science, Information Systems

Hardware-Based Spiking Neural Network Using a TFT-Type AND Flash Memory Array Architecture Based on Direct Feedback Alignment

Won-Mook Kang et al.

Summary: The hardware-based neural network with thin-film transistor-type AND flash memory array architecture allows on-chip training and improves memory operation efficiency. The DFA algorithm enables efficient neural network design without the need for equal synaptic weights in the forward and backward paths. Additionally, pulse schemes tailored for the AND array architecture contribute to achieving high recognition accuracy in pattern learning tasks.

IEEE ACCESS (2021)

Add to Collection

Article Multidisciplinary Sciences

Fully hardware-implemented memristor convolutional neural network

Peng Yao et al.

NATURE (2020)

Add to Collection

Article Nanoscience & Nanotechnology

Back-End, CMOS-Compatible Ferroelectric Field-Effect Transistor for Synaptic Weights

Mattia Halter et al.

ACS APPLIED MATERIALS & INTERFACES (2020)

Add to Collection

Article Engineering, Electrical & Electronic

High-Throughput In-Memory Computing for Binary Deep Neural Networks With Monolithically Integrated RRAM and 90-nm CMOS

Shihui Yin et al.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Resistive Crossbars as Approximate Hardware Building Blocks for Machine Learning: Opportunities and Challenges

Indranil Chakraborty et al.

PROCEEDINGS OF THE IEEE (2020)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic

3D AND: A 3D Stackable Flash Memory Architecture to Realize High-Density and Fast-Read 3D NOR Flash and Storage-Class Memory

Hang-Ting Lue et al.

2020 IEEE INTERNATIONAL ELECTRON DEVICES MEETING (IEDM) (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Highly Reliable Inference System of Neural Networks Using Gated Schottky Diodes

Suhwan Lim et al.

IEEE JOURNAL OF THE ELECTRON DEVICES SOCIETY (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

In situ training of feed-forward and recurrent convolutional memristor networks

Zhongrui Wang et al.

NATURE MACHINE INTELLIGENCE (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Neuro-Inspired Computing With Emerging Nonvolatile Memory

Shimeng Yu

PROCEEDINGS OF THE IEEE (2018)

Add to Collection

Article Multidisciplinary Sciences

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

Can Li et al.

NATURE COMMUNICATIONS (2018)

Add to Collection

Article Engineering, Electrical & Electronic

Fully memristive neural networks for pattern classification with unsupervised learning

Zhongrui Wang et al.

NATURE ELECTRONICS (2018)

Add to Collection

Article Chemistry, Multidisciplinary

Mimicking biological neurons with a nanoscale ferroelectric transistor

Halid Mulaosmanovic et al.

NANOSCALE (2018)

Add to Collection

Article Engineering, Electrical & Electronic

Resistive Random Access Memory for Future Information Processing System

Huaqiang Wu et al.

PROCEEDINGS OF THE IEEE (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Programming Protocol Optimization for Analog Weight Tuning in Resistive Memories

Ligang Gao et al.

IEEE ELECTRON DEVICE LETTERS (2015)

Add to Collection

Article Engineering, Electrical & Electronic

Experimental Demonstration and Tolerancing of a Large-Scale Neural Network (165 000 Synapses) Using Phase-Change Memory as the Synaptic Weight Element

Geoffrey W. Burr et al.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2015)

Add to Collection

Article Nanoscience & Nanotechnology

High precision tuning of state for memristive devices by adaptable variation-tolerant algorithm

Fabien Alibart et al.

NANOTECHNOLOGY (2012)

Add to Collection

© Peeref 2019-2024. All rights reserved.