Results 241 to 250 of about 220,848 (275)

Optical finite impulse response neural networks

Applied Optics, 2002
The 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, G S, Pati, Kelvin H, Wagner   +2 more
openaire   +2 more sources

Trainable optically programmed neural network

Applied Optics, 1992
The 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

Optical Neural Network Architecture in Photoferroelectrics

Ferroelectrics, 2003
We present a novel, versatile optoelectronic neural network architecture for implementing supervised learning in photo-ferroelectrics (Sr x Ba 1-x Nb 2 O 6 , Bi 12 XO 20 ; X=Ge, Si, Ti, LiNbO 3 :Fe, LiTaO 3 :Fe and LiTaO 3 :Cr). The system is based on spatial multiplexing rather than the more commonly used angular multiplexing of interconnect gratings.
Babur Y., Mamedov A.M.
openaire   +2 more sources

Optical pseudoinverse neural network

Optical Society of America Annual Meeting, 1990
Pseudoinverse is a linear mapping algorithm that produces minimum-squared errors. Pseudoinverse neural networks (PNNs) implement this algorithm by using neuralnetwork components in a two-layer structure. The first layer with N neurons is trained with a Kittler-Young transform and a pseudoinverse transform by using a set of training images from all ...
John X. Li, Francis T. S. Yu
openaire   +1 more source

Two-dimensional programmable optical neural network

Applied Optics, 1989
A 2-D hybrid optical neural network using a high resolution video monitor as a programmable associative memory is proposed. Experiments and computer simulations of the system have been conducted. The high resolution and large dynamic range of the video monitor enable us to implement a hybrid neural network with more neurons and more accurate operation.
T, Lu, S, Wu, X, Xu, F T, Yu
openaire   +2 more sources

Holographic-disk-based optical neural network

Optics Letters, 1992
Holographic photothermoplastic disks with two-dimensional Fourier hologram registration obtained by infrared laser heating of the recording layer is described. These disks have high information recording density (~10(5) bits/mm(2)), high quality of the registered Fourier holograms (eta = 5-7%, contrast ratio 70:1), the possibility of information ...
A, Kutanov, B, Abdrisaev, S, Dordoev
openaire   +2 more sources

Mirror-array optical interconnected neural network

Optics Letters, 1991
A high-light-efficiency optical neural network that uses a mirror-array interconnection is proposed. Design considerations for the mirror array and experimental demonstration are given.
F T, Yu, X, Yang, S, Yin, D A, Gregory
openaire   +2 more sources

Neural network model for extracting optic flow

Neural Networks, 2005
When we travel in an environment, we have an optic flow on the retina. Neurons in the area MST of macaque monkeys are reported to have a very large receptive field and analyze optic flows on the retina. Many MST-cells respond selectively to rotation, expansion/contraction and planar motion of the optic flow.
Kazuya, Tohyama, Kunihiko, Fukushima
openaire   +2 more sources

Programmable optical neural networks

Optical Society of America Annual Meeting, 1992
We have developed an optical neurocomputer for implementing neural networks based on real-time holography in photorefractive materials. Optical techniques show great promise for implementing neural network models because of the parallelism, connectivity, and high storage capacity of optics.
openaire   +1 more source

Optical neural networks based on optical interconnection

WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000, 2002
An optical signal has the characteristics of interconnection and parallelism; it can be processed and transferred through complex amplitude, full parallel, high performance and jillion interconnection. This paper introduces the characteristics and physical essence of optical interconnection.
null Fu Zhanping, null Liu Zhaohui, null Xu Zhaolin   +2 more
openaire   +1 more source