Results 131 to 140 of about 263,497 (176)
Some of the next articles are maybe not open access.
Spatial Light Modulators and Applications, 1990
Spatial light modulators (SLMs) play an essential role in almost every optical implementation of neural networks. They are used to perform some or all of the functions of input, neural states and interconnection pattern. If we take a very broad encompassing definition of SLMs to include one- and two-dimensional LED arrays and perhaps even fixed masks ...
Bernard H. Softer +2 more
openaire +2 more sources
Spatial light modulators (SLMs) play an essential role in almost every optical implementation of neural networks. They are used to perform some or all of the functions of input, neural states and interconnection pattern. If we take a very broad encompassing definition of SLMs to include one- and two-dimensional LED arrays and perhaps even fixed masks ...
Bernard H. Softer +2 more
openaire +2 more sources
Optical disk-based neural network
Annual Meeting Optical Society of America, 1989The rapid growth of optical disk storage techniques provides an advantage for optics in large capacity information storage and processing. Here we propose an optical disk-based neural network architecture for high speed and large capacity associative processing.
T, Lu, K, Choi, S, Wu, X, Xu, F T, Yu
openaire +2 more sources
Optical computing powers graph neural networks
Applied Optics, 2022Graph-based neural networks have promising perspectives but are limited by electronic bottlenecks. Our work explores the advantages of optical neural networks in the graph domain. We propose an optical graph neural network (OGNN) based on inverse-designed optical processing units (OPUs) to classify graphs with optics.
Kaida Tang +5 more
openaire +2 more sources
Optical neural network with bipolar neural states
Applied Optics, 1992A method to achieve bipolar performance in a single-channel optical associative memory is presented. By coding the biased interconnection weights, a distributed background, and an input-dependent dynamic threshold on a single mask, we construct an optical network with both bipolar neural states and bipolar interconnections.
X M, Wang, G G, Mu
openaire +2 more sources
Optics and Photonics News, 2020
Light-based computers inspired by the human brain could transform machine learning—if they can be scaled up.
openaire +1 more source
Light-based computers inspired by the human brain could transform machine learning—if they can be scaled up.
openaire +1 more source
Space-time sharing optical neural network
Optical Society of America Annual Meeting, 1990The massive interconnection and parallel operation in an optical neural network (ONN) require a high-resolution, large-dynamic-range spatial light modulator (SLM) for the construction of the interconnectionweight matrix (IWM). However, the resolution of currently available SLM's is limited, and this is a major obstacle in the development of a large ...
F T, Yu, X, Yang, T, Lu
openaire +2 more sources
Diffractive optical neural networks
AI and Optical Data Sciences II, 2021We introduce a diffractive optical neural network architecture that can all-optically implement various functions, following the deep learning-based design of passive layers that work collectively. We created 3D-printed diffractive networks that implement all-optical classification of images of handwritten digits and fashion products as well as the ...
openaire +1 more source
Photorefractive optical neural network
SPIE Proceedings, 1990An account is given of the self-pumped optical neural network (SPONN) fine-grained optical architecture, which features massive parallelism and much higher interconnectivity than either bus-oriented or hypercube electronic architectures. Connections among neurons are implemented by SPONN as sets of angularly and spatially multiplexed volume phase ...
Bernard H. Soffer +2 more
openaire +1 more source
Optical quadratic neural networks
Annual Meeting Optical Society of America, 1988Recently several articles have discussed the advantages of higher-order neural networks.1 These include shorter learning times, increased memory storage capacities, and more flexible pattern decision boundaries. Problems that cannot be solved by linear neural networks without hidden layers can be easily solved by looking at higher- order correlations ...
A. P. Ittycheriah +2 more
openaire +1 more source
Optical finite impulse response neural networks
Applied Optics, 2002The finite impulse response neural network is described in detail. Different algorithms capable of temporal back-propagation are considered, including a novel modification to the conventional algorithm, called the delayed-feedback back-propagation algorithm.
Paulo E X, Silveira +2 more
openaire +2 more sources