Results 91 to 100 of about 5,938,476 (293)

Multimode Oxide‐Based Optoelectronic Memtransistor for In‐Sensor Vision Processing

Advanced Functional Materials, EarlyView.
A multimode optoelectronic memtransistor (OEMT) is demonstrated for vision explainable artificial intelligence (VXAI) hardware. By integrating optical sensing, electrical masking, and non‐volatile memory, the device enables key operations required for generating saliency information.
Min Gu Lee, Geunyoung Kim, Hwa Young Kim, Do Hoon Kim, Hanchan Song, Huisu Noh, Jungwan Noh, Seungwoo Lee, Sang‐Hee Ko Park, Himchan Cho, Kyung Min Kim   +10 more
wiley   +1 more source

Reconfigurable optical neural networks with Plug-and-Play metasurfaces

Opto-Electronic Advances
In a very recent study, Prof. Lingling Huang and co-workers proposed and demonstrated reconfigurable optical neural networks based on cascaded metasurfaces.
Yongmin Liu, Yuxiao Li
doaj   +1 more source

Multimodal Optoelectronic Synapses for Neuromorphic Intelligence: Coupling Light, Electrical, Thermal, and Beyond

Advanced Functional Materials, EarlyView.
This review revisits optoelectronic neuromorphic devices that extend from unimodal sensing toward multimodal perception. Five types of stimuli‐to‐output information flow that are classified based on the device roles within the system and applications are summarized and discussed.
Jihyun Shin, Junhyung Cho, Wangmyung Choi, Jaehyun Hur, Jae Kyeong Jeong, Ulrike Kraft, Hocheon Yoo   +6 more
wiley   +1 more source

Photonics Breakthroughs 2024: Nonlinear Photonic Computing at Scale

IEEE Photonics Journal
A photonic neural network utilizes photons instead of electrons to process information, with the prospect of higher computing efficiency, lower power consumption, and reduced latency.
Hao Wang, Jianqi Hu, Andrea Morandi, Alfonso Nardi, Fei Xia, Xuanchen Li, Romolo Savo, Qiang Liu, Rachel Grange, Sylvain Gigan   +9 more
doaj   +1 more source

Multi-objective optimization of SOI-based Mach-Zehnder modulators employing deep neural networks and a non-dominant genetic algorithm

We combine an artificial neural network model of an integrated Mach-Zehnder modulator with a multi-objective optimization algorithm to optimize the modulator's parameters.
Hernandez-Figueroa, Hugo Enrique, De Paula, Romulo, Aldaya, Ivan [UNESP], Abreu, Leandra [UNESP], Sutili, Tiago, Figueiredo, Rafael C., Bustamante, Yesica R. R.   +6 more
core   +1 more source

Towards neural-symbolic integration: the evolutionary neural logic networks [PDF]

, 2004
This work presents the application of a new methodology for the production of neural logic networks into two real-world problems from the medical domain.
Tsakonas, Athanasios, A. Tsakonas
core   +1 more source

Light‐Induced Field‐Tunneling Synapses in Solution‐Processed Van Der Waals Heterostructures for Scalable, Retina‐Inspired Optical Sensing

Advanced Functional Materials, EarlyView.
A scalable, solution‐processed WSe2/ZrO2‐x van der Waals heterostructure realizes a light‐induced field‐tunneling synapse (LIFTS) that activates exclusively under bright illumination, emulating the photopic adaptation of the human retina at the device level.
Kijeong Nam, Jihyun Kim, Soobeen Ji, In Soo Kim, Sejin Kim, Eungseon Yeon, Do Kyung Hwang, Iva Plutnarová, Zdeněk Sofer, Sang Min Won, Joohoon Kang   +10 more
wiley   +1 more source

Memristive‐Gated RC‐Delay Synaptic Transistors for Time‐Encoded Analog in‐Memory Computing

Advanced Functional Materials, EarlyView.
A Memristive‐Gated Transistor for Time‐Encoded Analog In‐Memory Computing — By exploiting the RC delay of a self‐rectifying interface‐type memristor, nonlinear I–V distortion is structurally bypassed, enabling 3‐bit nonvolatile memory, spike‐timing‐based analog encoding, and hardware‐calibrated reservoir‐computing validation within a unified device ...
Yun‐Seo Shin, Eunjoo Yoo, Ki‐Hoon Son, Hyun‐Sik Kim, Dae‐Hee Han, Jeong Hyeon Son, Seung Hwan Lee, Hong‐Sub Lee   +7 more
wiley   +1 more source

Flexible orbital angular momentum mode switching in multimode fibre using an optical neural network chip

Light: Advanced Manufacturing
Mode-division multiplexing technology has been proposed as a crucial technique for enhancing communication capacity and alleviating growing communication demands.
Zhengsen Ruan, Yuanjian Wan, Lulu Wang, Wei Zhou, Jian Wang   +4 more
doaj   +1 more source

Emerging Post‐CMOS Hardware Neurons for Brain‐Inspired Computing: Devices, Circuits, and System Integration

Advanced Functional Materials, EarlyView.
The physical realization of artificial neurons is a critical challenge for energy‐efficient neuromorphic computing. This review presents a comprehensive analysis of the evolution of artificial neuron implementations from conventional CMOS to emerging post‐CMOS technologies.
Kannan Udaya Mohanan, Hocheon Yoo, Benoît H. Lessard, Ioannis Kymissis, Chang‐Hyun Kim   +4 more
wiley   +1 more source