Results 261 to 270 of about 5,938,476 (293)
Some of the next articles are maybe not open access.
Demonstration of an optical inhibitory neural network
Optics Letters, 1989An optical inhibitory neural network with lateral interconnections between units is demonstrated. Separate device responses, inversely proportional and sigmoid, are utilized for inhibitory and excitatory units, respectively. Preliminary experimental results for an edge enhancement illustrate the versatility of the network.
W, Kawakami, H, Yoshinaga, K, Kitayama
openaire +2 more sources
Optical hardware backpropagation neural network
IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), 2003Optical error backpropagation is experimentally demonstrated in a feedforward optical neural network developed by the authors. To our knowledge, this is the first report of hardware backpropagation training in an optical system. The network uses the trainable light steering behavior of an optical nonlinear material to implement both neural processing ...
Steven R. Skinner +4 more
openaire +2 more sources
Optically excited synapse for neural networks
Applied Optics, 1987What can optics with its promise of parallelism do for neural networks which require matrix multipliers? An all optical approach requires optical logic devices which are still in their infancy. An alternative is to retain electronic logic while optically addressing the synapse matrix.
openaire +2 more sources
Optical Positioning Using Neural Network
2018 41st International Conference on Telecommunications and Signal Processing (TSP), 2018This paper describes passive measurement of an object (camera) position based on the position of optical beacon. The optical beacon consists of light sources that are arranged in a specific geometric pattern. Due to the change of the camera position against the beacon, there is also a change in the mutual position of the light sources in the image ...
Martin Polasek, Jiri Nemecek 0001
openaire +2 more sources
Trainable optically programmed neural network
Applied Optics, 1992The use of a two-dimensional photoconductive sensor array that is coupled with a liquid-crystal display is examined as a basis for the hardware implementation of neural network architectures. An array of 128 x 128 amorphous-silicon photoconductors of lateral geometry is fabricated and mated to a liquid-crystal device, the latter of which is used to ...
openaire +2 more sources
Backpropagation Through Nonlinear Units for the All-Optical Training of Neural Networks
Photonics Research, 2021Thomas Daniel Barrett +2 more
exaly
A Survey of Approaches for Implementing Optical Neural Networks
Optics and Laser Technology, 2021Runqin Xu, Yishi Shi
exaly
How Do Neural Networks Estimate Optical Flow? A Neuropsychology-Inspired Study
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022Guido de Croon +2 more
exaly
Multi-Layer Optical Fourier Neural Network Based on the Convolution Theorem
AIP Advances, 2021Guohua Gu, Qian Chen, Jia Liu
exaly
Chip-Based High-Dimensional Optical Neural Network
Nano-Micro Letters, 2022Xingcai Zhang, Bohan Chen
exaly