Results 71 to 80 of about 68,095 (317)

On Training Spiking Neural Networks by Means of a Novel Quantum Inspired Machine Learning Method

Applied AI Letters
In spite of the high potential shown by spiking neural networks (e.g., temporal patterns), training them remains an open and complex problem. In practice, while in theory these networks are computationally as powerful as mainstream artificial neural ...
Jean Michel Sellier, Alexandre Martini
doaj   +1 more source

Spike-Timing Dependent Learning Dynamics in Silicon-Doped Hafnium-Oxide-Based Ferroelectric Field Effect Transistors

IEEE Journal of the Electron Devices Society
Brain-inspired computing, with its potential for energy-efficient spatio-temporal data processing, has spurred significant interest in spiking neural networks and their hardware implementations. Leveraging their non-volatile memory and analog tunability,
Masud Rana Sk, Apu Das, Gautham Kumar, Deepanshi Bhatnagar, Sourodeep Roy, Yannick Raffel, Maximilian Lederer, Konrad Seidel, Sourav De, Bhaswar Chakrabarti   +9 more
doaj   +1 more source

Steep‐Switching Memory FET for Noise‐Resistant Reservoir Computing System

Advanced Functional Materials, EarlyView.
We demonstrate the steep‐switching memory FET with CuInP2S6/h‐BN/α‐In2Se3 heterostructure for application in noise‐resistant reservoir computing systems. The proposed device achieves steep switching characteristics (SSPGM = 19 mV/dec and SSERS = 23 mV/dec) through stabilization between CuInP2S6 and h‐BN.
Seongkweon Kang, Jaerok Kim, Sang‐Min Lee, Sungpyo Baek, Saeroonter Oh, Yoonmyung Lee, Sungjoo Lee   +6 more
wiley   +1 more source

Neural dynamics as sampling: a model for stochastic computation in recurrent networks of spiking neurons. [PDF]

PLoS Computational Biology, 2011
The organization of computations in networks of spiking neurons in the brain is still largely unknown, in particular in view of the inherently stochastic features of their firing activity and the experimentally observed trial-to-trial variability of ...
Lars Buesing, Johannes Bill, Bernhard Nessler, Wolfgang Maass   +3 more
doaj   +1 more source

Modeling spiking neural networks

Theoretical Computer Science, 2008
AbstractA notation for the functional specification of a wide range of neural networks consisting of temporal or non-temporal neurons, is proposed. The notation is primarily a mathematical framework, but it can also be illustrated graphically and can be extended into a language in order to be automated. Its basic building blocks are processing entities,
Zaharakis, Ioannis D., Kameas, Achilles D.   +1 more
openaire   +1 more source

An Ultra‐Robust Memristor Based on Vertically Aligned Nanocomposite with Highly Defective Vertical Channels for Neuromorphic Computing

Advanced Functional Materials, EarlyView.
An ultra‐robust memristor based on SrTiO3‐CeO2 (S‐C) vertically aligned nanocomposite (VAN) achieving exceptional endurance of 1012 switching cycles via interface engineering. Artificial neural networks (ANNs) integrated with S‐C VAN memristors exhibit high training accuracy across multiple datasets.
Zedong Hu, Hongyi Dou, Jeremy B. Gan, Cun Li, Xuanyu Sheng, Juanjuan Lu, Abhijeet Choudhury, Jialong Huang, Yizhi Zhang, Zhongxia Shang, Ye Cao, Xinghang Zhang, Haiyan Wang   +12 more
wiley   +1 more source

Dynamic Control of Synaptic Plasticity by Competing Ferroelectric and Trap‐Assisted Switching in IGZO Transistors with Al2O3/HfO2 Dielectrics

Advanced Functional Materials, EarlyView.
A frequency‐tunable ferroelectric synaptic transistor based on a buried‐gate InGaZnO channel and Al2O3/HfO2 dielectric stack exhibits linear and reversible weight updates using single‐polarity pulses. By switching between ferroelectric and trap‐assisted modes depending on input frequency, the device simplifies neuromorphic circuit design and achieves ...
Ojun Kwon, Dong Ho Lee, Seyoung Oh, Jongwon Yoon, Hyo‐Bae Kim, Ji‐Hoon Ahn, Woojin Park, Han Seul Kim, Byungjin Cho   +8 more
wiley   +1 more source

Multicolor Optoelectronic Synapse Enabled by Photon‐Modulated Remote Doping in Solution‐Processed Van Der Waals Heterostructures

Advanced Functional Materials, EarlyView.
Multicolor optoelectronic synapses are realized by vertically integrating solution‐processed MoS2 thin‐film and SWCNT. The electronically disconnected but interactive MoS2 enables photon‐modulated remote doping, producing a bi‐directional photoresponse.
Jihyun Kim, Hyunbin Kim, Gang Jin Cheon, Dohyun Lee, In Soo Kim, Uiyeon Won, Jongseok Lee, Sang Min Won, Joohoon Kang   +8 more
wiley   +1 more source

A framework for the general design and computation of hybrid neural networks

Nature Communications, 2022
Hybrid neural networks combine advantages of spiking and artificial neural networks in the context of computing and biological motivation. The authors propose a design framework with hybrid units for improved flexibility and efficiency of hybrid neural ...
Rong Zhao, Zheyu Yang, Hao Zheng, Yujie Wu, Faqiang Liu, Zhenzhi Wu, Lukai Li, Feng Chen, Seng Song, Jun Zhu, Wenli Zhang, Haoyu Huang, Mingkun Xu, Kaifeng Sheng, Qianbo Yin, Jing Pei, Guoqi Li, Youhui Zhang, Mingguo Zhao, Luping Shi   +19 more
doaj   +1 more source

Configuring spiking neural network training algorithms [PDF]

, 2017
Spiking neural networks, based on biologically-plausible neurons with temporal information coding, are provably more powerful than widely used artificial neural networks based on sigmoid neurons (ANNs).
Mustari, Mst Mausumi Sabnam
core