Results 101 to 110 of about 5,938,476 (293)
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 +5 more
openaire +2 more sources
Training hybrid neural networks with multimode optical nonlinearities using digital twins
The ability to train ever-larger neural networks brings artificial intelligence to the forefront of scientific and technical discoveries. However, their exponentially increasing size creates a proportionally greater demand for energy and computational ...
Suter, Louis J.E. +6 more
core +1 more source
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 +4 more
wiley +1 more source
Intelligent ComputingOptical neural networks (ONNs) have recently attracted extensive interest as potential alternatives to electronic artificial neural networks, owing to their intrinsic capabilities in parallel signal processing with reduced power consumption and low ...
Yi-Feng Liu +9 more
doaj +1 more source
On the implementation of nonlinearities in optical neural networks: opinion
Optical neural networks are expected to be hybrid systems for the foreseeable future combining optics and electronics. The linear portion of the system, consisting of the weighted interconnections between the neurons, can be realized optically.
Yildirim, Mustafa +4 more
core +1 more source
All-optical interconnection of broadband optical customer networks
, 2022 Transparent optical networks will become more and more important in the near future. Therefore a key issue for future optical networking is the all-optical interconnection of existing, independent networks.
Hermes, T. +3 more
core
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 +3 more
wiley +1 more source
Strategies for training optical neural networks
National Science Open, 2022 Yang Qipeng +3 more
doaj +1 more source
Electrical‐Programming‐Free Neural Crossbars Enabled by Photochemical Weight Patterning
Advanced Functional Materials, EarlyView.A flexible neural‐crossbar hardware system enabled by electrical‐programming‐free, mask‐defined, array‐parallel photochemical weight patterning is demonstrated. Trained weights are physically implemented across the array, supporting multilevel programming, bending‐stable operation and reconfiguration, substrate reuse, and low‐energy readout while ...
Hyo‐Bin Jang +5 more
wiley +1 more source
Scaling up for end-to-end on-chip photonic neural network inference
Light: Science & ApplicationsOptical neural networks are emerging as a competitive alternative to their electronic counterparts, offering distinct advantages in bandwidth and energy efficiency.
Bo Wu +6 more
doaj +1 more source