Results 111 to 120 of about 7,242,720 (244)

Generative Adversarial Optical Networks Using Diffractive Layers for Digit and Action Generation

Photonics
Within the traditional electronic neural network framework, Generative Adversarial Networks (GANs) have achieved extensive applications across multiple domains, including image synthesis, style transfer and data augmentation.
Pei Hu, Tengyu Cui, Yuanyuan Zhang, Shuai Feng   +3 more
doaj   +1 more source

Engineered Nanotopography to Modulate Growth and Signaling of Neuronal Networks

Advanced Functional Materials, EarlyView.
This study examines the interaction between neurons and nanoscale topographies on engineered substrates. Neurons cultured on nanowires, nanopillars and nanoneedles exhibit enhanced neurite outgrowth, form more organized neuronal circuits, and display improved synaptic connectivity, compared to flat substrates.
Hao Nguyen Tran, Kalyan Shobhana, Zlatan Trifunovic, Dan Smith, Michael Stuiber, Chennupati Jagadish, Mirella Dottori, Andrea J. O'Connor, Vini Gautam   +8 more
wiley   +1 more source

On-Chip Optical Convolutional Neural Networks

CoRR, 2018
Convolutional Neural Networks (CNNs) are a class of Artificial Neural Networks(ANNs) that employ the method of convolving input images with filter-kernels for object recognition and classification purposes. In this paper, we propose a photonics circuit architecture which could consume a fraction of energy per inference compared with state of the art ...
Hengameh Bagherian, Scott A. Skirlo, Yichen Shen 0001, Huaiyu Meng, Vladimir Ceperic, Marin Soljacic   +5 more
openaire   +2 more sources

Bio‐Inspired Artificial Ionic Mechanoreceptor

Advanced Functional Materials, EarlyView.
A skin‐inspired artificial mechanoreceptor based on ionic interactions is presented for biomimetic tactile sensing. Pressure‐driven ionic redistribution within microfluidic channels generates a self‐powered electrical signal without external bias. The generated waveform exhibits mechanoreceptor‐like temporal features, including overshoot and undershoot,
Mohammad Akbari, Jeppe Don, Lasse A. N. Pedersen, John Noee, Rassoul Tabassian   +4 more
wiley   +1 more source

Noise-Robust Loop-Based Deep Optical Convolutional Neural Network

Photonics
We demonstrate a loop-based deep optical convolutional neural network that reuses a single free-space optical hardware to realize network depth through repeated passes.
Maryam Dehbashizadeh Chehreghan, Ripalta Stabile   +1 more
doaj   +1 more source

Multistage, Self‐Sensing Artificial Muscles With Coordination From Liquid Crystal Elastomer‐Graphene Composite Fibers

Advanced Functional Materials, EarlyView.
Inspired by skeletal muscles’ precision and endurance, CoilLCE integrates a self‐sensing liquid crystal elastomer/graphene artificial muscle with an embedded Joule‐heating copper coil, enabling closed‐loop multistage actuation with programmable intermediate states (strain accuracy of 2%), and antagonistic coordination (32% total strain). These features
Ziyun Zhang, Xuelin Wu, Yinding Chi, Qingya Huang, Yaoye Hong, Antonio Proctor Martinez, Jingxian Wu, Bingzhi He, Cynthia Sung, Shu Yang   +9 more
wiley   +1 more source

Quantum-Inspired Neural Network Model of Optical Illusions

Algorithms
Ambiguous optical illusions have been a paradigmatic object of fascination, research and inspiration in arts, psychology and video games. However, accurate computational models of perception of ambiguous figures have been elusive.
Ivan S. Maksymov
doaj   +1 more source

Physics‐Grounded Materials Artificial Intelligence for Reliable Materials Discovery

Advanced Functional Materials, EarlyView.
Physics‐Grounded Materials AI (PhysMat AI) integrates physical priors, descriptors, constraints, verification, and data infrastructure into a unified full‐stack framework, enabling reliable, interpretable, and autonomous AI‐driven materials discovery.
Yuhang Wang, Qian Wang, Seong‐Hoon Jang, Hao Li   +3 more
wiley   +1 more source

Optical neural networks: progress and challenges

Light: Science & Applications
AbstractArtificial intelligence has prevailed in all trades and professions due to the assistance of big data resources, advanced algorithms, and high-performance electronic hardware. However, conventional computing hardware is inefficient at implementing complex tasks, in large part because the memory and processor in its computing architecture are ...
Tingzhao Fu, Jianfa Zhang, Run Sun, Yuyao Huang, Wei Xu, Sigang Yang, Zhihong Zhu, Hongwei Chen   +7 more
openaire   +3 more sources

An artificial neural network for dimensions and cost modelling of internal micro-channels fabricated in PMMA using Nd:YVO4 laser [PDF]

, 2011
For micro-channel fabrication using laser micro-machining processing, estimation techniques are normally utilised to develop an approach for the system behaviour evaluation.
Brabazon, Dermot, Karazi, Shadi
core   +2 more sources