Results 151 to 160 of about 10,517,225 (330)

Bioinspired Fully On‐Chip Learning Implemented on Memristive Neural Networks

open access: yesAdvanced Intelligent Systems, EarlyView.
This work proposes a memristive neural network based on van der Waals ferroelectric memristors and contrastive Hebbian learning, enabling fully on‐chip learning. The system achieves over 98% accuracy in pattern recognition with low power consumption (0.321 nJ/image) and high robustness, paving the way for efficient, bioinspired neuromorphic computing ...
Zhixing Wen   +9 more
wiley   +1 more source

Memimpedance‐Based Biomolecular Device for Adaptive Physical Reservoir Computing

open access: yesAdvanced Intelligent Systems, EarlyView.
By integrating fast‐switching ion‐channel‐based memristive and slow‐switching biomembrane‐based memcapacitive nodes within droplet interface bilayers, this hybrid memimpedance reservoir overcomes the memory‐nonlinearity trade‐off and extends temporal adaptability.
Ahmed S. Mohamed   +3 more
wiley   +1 more source

Harnessing Nonidealities in Analog In‐Memory Computing Circuits: A Physical Modeling Approach for Neuromorphic Systems

open access: yesAdvanced Intelligent Systems, EarlyView.
This work harnesses nonidealities in analog in‐memory computing (IMC) by training physical neural networks modeled with ordinary differential equations. A differentiable spike‐time discretization accelerates training by 20× and reduces memory usage by 100×, enabling large IMC‐equivalent models to learn the CIFAR‐10 dataset.
Yusuke Sakemi   +5 more
wiley   +1 more source

Optoelectronic Neuromorphic System Based on Amorphous Indium–Gallium–Zinc–Oxide Thin‐Film Transistor for Spiking Neural Networks

open access: yesAdvanced Intelligent Systems, EarlyView.
An amorphous indium–gallium–zinc–oxide (IGZO)‐based optoelectronic neuromorphic system integrating light guides is introduced. The IGZO‐based optoelectronic synaptic transistor demonstrates high retention through a negative gate bias and emulates synaptic plasticity.
Yumin Yun   +6 more
wiley   +1 more source

Neuromorphic Device Based on Material and Device Innovation toward Multimode and Multifunction

open access: yesAdvanced Intelligent Systems, EarlyView.
In the era of big data, multimodal and multifunctional neuromorphic devices offer significant opportunities in designing AI hardware. In this work, recent advances about emerging material systems and novel device structures in this field are summarized in detail. Potential applications are reviewed.
Feng Guo   +3 more
wiley   +1 more source

High-throughput synaptic connectivity mapping using in vivo two-photon holographic optogenetics and compressive sensing. [PDF]

open access: yesNat Neurosci
Chen IW   +7 more
europepmc   +1 more source

Home - About - Disclaimer - Privacy