4.8 Article

A Memristors-Based Dendritic Neuron for High-Efficiency Spatial-Temporal Information Processing

Related references

Note: Only part of the references are listed.
Article Engineering, Electrical & Electronic

Dual-mode dendritic devices enhanced neural network based on electrolyte gated transistors

Zhaokun Jing et al.

Summary: As a fundamental component of biological neurons, dendrites play a crucial role in neuronal activities. In this study, a dual-mode dendritic device based on electrolyte gated transistor is proposed, which can generate both supralinear and sublinear current-voltage responses when receiving input voltage pulses. By using the dual-mode dendritic devices as a processing block between weight matrices and output neurons, the expression ability of neural networks can be dramatically enhanced. The constructed dual-mode dendrites-enhanced neural network achieves high efficiency in neuromorphic computing with a significant reduction in trainable parameters.

SEMICONDUCTOR SCIENCE AND TECHNOLOGY (2022)

Article Nanoscience & Nanotechnology

Investigation of Resistive Switching Mechanisms in Ti/TiOx/Pd-Based RRAM Devices

Ruofei Hu et al.

Summary: This paper investigates two distinct types of resistive switching in Ti/TiOx/Pd-based RRAM devices: filamentary resistive switching and dynamic resistive switching. Filamentary resistive switching is caused by spikes in the bottom Pd electrode, while dynamic resistive switching occurs when the bottom electrode is flat without spikes, resulting in dynamic changes in device resistance over time.

ADVANCED ELECTRONIC MATERIALS (2022)

Article Computer Science, Information Systems

Memristor-based signal processing for edge computing

Han Zhao et al.

Summary: This article reviews recent progress on memristor-based signal processing methods from the perspective of edge computing, focusing on signal preprocessing, feature extraction, signal classification and regression, and end-to-end signal processing. Memristors serve as critical accelerators to greatly improve system performance, particularly in terms of power efficiency and processing speed. The article also discusses existing challenges and future outlooks for memristor-based signal processing systems.

TSINGHUA SCIENCE AND TECHNOLOGY (2022)

Article Physics, Condensed Matter

Oscillation neuron based on a low-variability threshold switching device for high-performance neuromorphic computing

Yujia Li et al.

Summary: The paper introduces an oscillation neuron based on a low-variability Ag nanodots (NDs) threshold switching (TS) device with low power consumption and high uniformity. Measurement results show that the neuron exhibits self-oscillation behavior under low voltage and can accurately evaluate RRAM synaptic weights.

JOURNAL OF SEMICONDUCTORS (2021)

Article Nanoscience & Nanotechnology

Engineering the Threshold Switching Response of Nb2O5-Based Memristors by Ti Doping

Shimul Kanti Nath et al.

Summary: Two metal-oxide-metal devices based on niobium oxide thin films exhibit non-linear electrical characteristics with applications in neuromorphic computing. Doping is shown to improve device reliability and allows for tuning of various characteristics, such as threshold voltage and negative differential resistance. Temperature-dependent current-voltage characteristics and modelling suggest that doping-induced reductions in resistance and thermal activation energy play a role in engineering device response.

ACS APPLIED MATERIALS & INTERFACES (2021)

Article Engineering, Electrical & Electronic

Oxygen Vacancy-Dependent Synaptic Dynamic Behavior of TiOx-Based Transparent Memristor

Yu She et al.

Summary: A transparent synaptic device based on a stack structure of ITO/TiOy/TiOx/TiN is fabricated with high transmittance, introducing an oxygen-deficient TiOy layer to adjust current characteristics. Different thickness ratios of the oxygen-deficient TiOy layer are designed for multilevel resistance state adjustability and analog resistive switching behavior. The device with the optimum thickness ratio offers excellent uniformity and nonlinearity for further simulation of essential synaptic functions.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2021)

Article Nanoscience & Nanotechnology

Energy-efficient Mott activation neuron for full-hardware implementation of neural networks

Sangheon Oh et al.

Summary: The research introduces an energy-efficient and compact Mott activation neuron based on vanadium dioxide, successfully integrated with a CBRAM crossbar array to achieve efficient in-memory computing. The Mott activation neuron outperforms analogue complementary metal-oxide semiconductor implementations and enables the implementation of activation functions in neural networks.

NATURE NANOTECHNOLOGY (2021)

Article Nanoscience & Nanotechnology

Metal-oxide interface reactions and their effect on integrated resistive/threshold switching in NbOx

Shimul Kanti Nath et al.

NANOTECHNOLOGY (2020)

Article Multidisciplinary Sciences

Fully hardware-implemented memristor convolutional neural network

Peng Yao et al.

NATURE (2020)

Review Nanoscience & Nanotechnology

Neuromorphic nanoelectronic materials

Vinod K. Sangwan et al.

NATURE NANOTECHNOLOGY (2020)

Article Chemistry, Multidisciplinary

Emerging Memristive Artificial Synapses and Neurons for Energy-Efficient Neuromorphic Computing

Sanghyeon Choi et al.

ADVANCED MATERIALS (2020)

Article Nanoscience & Nanotechnology

Power-efficient neural network with artificial dendrites

Xinyi Li et al.

NATURE NANOTECHNOLOGY (2020)

Article Computer Science, Artificial Intelligence

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

Jun Liu et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Article Chemistry, Multidisciplinary

Spatiotemporal Information Processing Emulated by Multiterminal Neuro-Transistor Networks

Yongli He et al.

ADVANCED MATERIALS (2019)

Article Multidisciplinary Sciences

Subthreshold firing in Mott nanodevices

Javier del Valle et al.

NATURE (2019)

Article Engineering, Electrical & Electronic

Improvement of NbOx-based threshold switching devices by implementing multilayer stacks

Melanie Herzig et al.

SEMICONDUCTOR SCIENCE AND TECHNOLOGY (2019)

Article Multidisciplinary Sciences

Equivalent-accuracy accelerated neural-network training using analogue memory

Stefano Ambrogio et al.

NATURE (2018)

Article Multidisciplinary Sciences

Biological plausibility and stochasticity in scalable VO2 active memristor neurons

Wei Yi et al.

NATURE COMMUNICATIONS (2018)

Article Multidisciplinary Sciences

Chaotic dynamics in nanoscale NbO2 Mott memristors for analogue computing

Suhas Kumar et al.

NATURE (2017)

Article Multidisciplinary Sciences

Physical origins of current and temperature controlled negative differential resistances in NbO2

Suhas Kumar et al.

NATURE COMMUNICATIONS (2017)

Article Multidisciplinary Sciences

Mastering the game of Go with deep neural networks and tree search

David Silver et al.

NATURE (2016)

Article Chemistry, Multidisciplinary

Biorealistic Implementation of Synaptic Functions with Oxide Memristors through Internal Ionic Dynamics

Chao Du et al.

ADVANCED FUNCTIONAL MATERIALS (2015)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Computer Science, Cybernetics

Spatiotemporal pattern formation in two-dimensional neural circuits: roles of refractoriness and noise

Pulin Gong et al.

BIOLOGICAL CYBERNETICS (2013)

Article Chemistry, Physical

A scalable neuristor built with Mott memristors

Matthew D. Pickett et al.

NATURE MATERIALS (2013)

Article Engineering, Electrical & Electronic

A Two-Dimensional Configurable Active Silicon Dendritic Neuron Array

Yingxue Wang et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS (2011)

Editorial Material Chemistry, Physical

O-Ti (Oxygen-Titanium)

H. Okamoto

JOURNAL OF PHASE EQUILIBRIA AND DIFFUSION (2011)

Article Chemistry, Multidisciplinary

Coexistence of Filamentary and Homogeneous Resistive Switching in Fe-Doped SrTiO3 Thin-Film Memristive Devices

Ruth Muenstermann et al.

ADVANCED MATERIALS (2010)

Article Multidisciplinary Sciences

Dendritic Discrimination of Temporal Input Sequences in Cortical Neurons

Tiago Branco et al.

SCIENCE (2010)

Article Materials Science, Multidisciplinary

Exponential ionic drift: fast switching and low volatility of thin-film memristors

Dmitri B. Strukov et al.

APPLIED PHYSICS A-MATERIALS SCIENCE & PROCESSING (2009)

Article Neurosciences

Pyramidal neuron as two-layer neural network

P Poirazi et al.

NEURON (2003)

Article Computer Science, Artificial Intelligence

Simple model of spiking neurons

EM Izhikevich

IEEE TRANSACTIONS ON NEURAL NETWORKS (2003)

Review Multidisciplinary Sciences

Diversity and dynamics of dendritic signaling

M Häusser et al.

SCIENCE (2000)