Results 91 to 100 of about 2,913 (243)

Oxide Semiconductor Memristor‐Based Optoelectronic Synaptic Devices With Quaternary Memory Storage

open access: yesAdvanced Electronic Materials
A pioneering integration of oxide semiconductor memristors with optoelectronic features is presented, surpassing binary limitations to realize multi‐valued synaptic operations.
Jeong‐Hyeon Kim   +8 more
doaj   +1 more source

A Photoelectric-Stimulated MoS2 Transistor for Neuromorphic Engineering

open access: yesResearch, 2019
The von Neumann bottleneck has spawned the rapid expansion of neuromorphic engineering and brain-like networks. Synapses serve as bridges for information transmission and connection in the biological nervous system.
Shuiyuan Wang   +7 more
doaj   +1 more source

Advances in optoelectronic artificial synapses

open access: yesCell Reports Physical Science, 2022
Ying Li, Guozhen Shen
openaire   +1 more source

An Artificial Optoelectronic Synapse Based on a Photoelectric Memcapacitor

open access: yesAdvanced Electronic Materials, 2019
AbstractThe rapid development of artificial intelligence technology has led to the urge for artificial optoelectronic synapses with visual perception and memory capabilities. A new type of artificial optoelectronic synapse, namely a photoelectric memcapacitor, is proposed and demonstrated.
Lei Zhao   +13 more
openaire   +1 more source

An On‐Demand Neuromorphic Vision System Enabled by a Multi‐Paradigm Neuromorphic Device and Hierarchical Reconfigurability Designed from Device to System Level

open access: yesAdvanced Science, EarlyView.
An on‐demand ultra‐reconfigurable intelligent vision system with hierarchical reconfigurability from device to system levels is demonstrated. Through co‐design of a multi‐paradigm device, reconfigurable circuits, and adaptive system architecture/algorithms, the system enables seamless switching among spiking, non‐spiking, neuromorphic imaging (NI), and
Biyi Jiang   +7 more
wiley   +1 more source

Integration of Freestanding High‐k Oxide Membranes for 2D Ferroelectric Field‐Effect Transistors

open access: yesAdvanced Science, EarlyView.
This work introduces a defect‐tolerant integration strategy that enables freestanding BaTiO3 membranes to form low‐leakage top‐gate junctions with MoS2. The resulting FeFETs exhibit a record 0.22 V nm−1 memory window, ultrahigh‐k response, and near‐ideal subthreshold swings.
Zejing Guo   +16 more
wiley   +1 more source

Analog Signal Summation for Reinforcement Learning via Simultaneous Light–Voltage Modulation in a Synaptic Device

open access: yesAdvanced Science, EarlyView.
To overcome limitations of conventional AI hardware, a light‐voltage dual‐modulating synaptic (LVDS) transistor using an IGZO/InAs quantum dot hybrid structure is proposed. LVDS transistor enables analog summation for Dueling Deep Q‐Networks by independently modulating memory via optical and electrical stimuli.
Dong Gue Roe   +10 more
wiley   +1 more source

Toward bio-inspired information processing with networks of nano-scale switching elements

open access: yes, 2013
Unconventional computing explores multi-scale platforms connecting molecular-scale devices into networks for the development of scalable neuromorphic architectures, often based on new materials and components with new functionalities. We review some work
Konkoli, Zoran, Wendin, Göran
core  

Single‐Crystal PZT‐Driven Organic Piezo‐Phototronic Adaptive Transistors Toward Advanced Spatiotemporal Visual Computing

open access: yesAdvanced Science, EarlyView.
Here, we propose a single‐crystal PZT‐based piezo‐phototronic organic adaptive memory transistor (OAMT), achieving a record memory window capacity factor (γ) of 0.87 at a low SS of 200 mV/decade via efficient multi‐field control. The device achieves a high recognition accuracy ∼ 90% in neuromorphic simulations, demonstrates robust fault tolerance under
Chenhao Xu   +8 more
wiley   +1 more source

In Situ Quantization with Memory‐Transistor Transfer Unit Based on Electrochemical Random‐Access Memory for Edge Applications

open access: yesAdvanced Science, EarlyView.
By combining ionic nonvolatile memories and transistors, this work proposes a compact synaptic unit to enable low‐precision neural network training. The design supports in situ weight quantization without extra programming and achieves accuracy comparable to ideal methods. This work obtains energy consumption advantage of 25.51× (ECRAM) and 4.84× (RRAM)
Zhen Yang   +9 more
wiley   +1 more source

Home - About - Disclaimer - Privacy