Results 31 to 40 of about 5,938,476 (293)
SPIE Proceedings, 1994 The trade-off between the number of neurons that can be implemented with a single correlator and the shift invariance that each neuron has is investigated. A new type of correlator implemented with a planar hologram is described whose shift invariance can be controlled by setting the position of the hologram properly.
Psaltis, Demetri, Levene, Michael
openaire +2 more sources
Correlating matched-filter model for analysis and optimisation of neural networks [PDF]
, 1989 A new formalism is described for modelling neural networks by means of which a clear physical understanding of the network behaviour can be gained.
Midwinter, J.E. +7 more
core +1 more source
Performance analysis of different DCNN models in remote sensing image object detection
EURASIP Journal on Image and Video Processing, 2022 In recent years, deep learning, especially deep convolutional neural networks (DCNN), has made great progress. Many researchers use different DCNN models to detect remote sensing targets. Different DCNN models have different advantages and disadvantages.
Huaijin Liu +3 more
doaj +1 more source
Optical frontend for a convolutional neural network
Applied Optics, 2019 The parallelism of optics and the miniaturization of optical components using nanophotonic structures, such as metasurfaces present a compelling alternative to electronic implementations of convolutional neural networks. The lack of a low-power optical nonlinearity, however, requires slow and energy-inefficient conversions between the electronic and ...
Shane Colburn +3 more
openaire +4 more sources
Lazy training of radial basis neural networks [PDF]
, 2006 Proceeding of: 16th International Conference on Artificial Neural Networks, ICANN 2006. Athens, Greece, September 10-14, 2006Usually, training data are not evenly distributed in the input space.
Galván, Inés M. +5 more
core +1 more source
A fibre optic sensor for the measurement of surface roughness and displacement using artificial neural networks [PDF]
, 1997 This paper presents a fiber optic sensor system, artificial neural networks (fast back-propagation) are employed for the data processing. The use of the neural networks makes it possible for the sensor to be used both for surface roughness and ...
Butler, C, Lu, Y, Zhang, K, Yang, QP
core +1 more source
Faster and More Accurate Geometrical-Optics Optical Force Calculation Using Neural Networks
, 2023 We use neural networks to improve not only the speed but also the accuracy of the optical force calculations in the geometrical-optics approximation.
Neves, Antonio A.R. +7 more
core +1 more source
Optical character recognition with neural networks
Вестник КазНУ. Серия математика, механика, информатика, 2019 XXI century is the age of global automation and digitization. There is high demand for optical recognition software, including character recognition. There are different approaches in solution optical recognition problem.
Aidarbek Shalakhmetov, Sanzhar Aubakirov
doaj +1 more source
An optical neural chip for implementing complex-valued neural network
Nature Communications, 2021 Most demonstrations of optical neural networks for computing have been so far limited to real-valued frameworks. Here, the authors implement complex-valued operations in an optical neural chip that integrates input preparation, weight multiplication and ...
H. Zhang +17 more
doaj +1 more source
All-optical Fourier neural network using partially coherent light
ChipOptical neural networks present distinct advantages over traditional electrical counterparts, such as accelerated data processing and reduced energy consumption.
Jianwei Qin +5 more
doaj +1 more source