Results 61 to 70 of about 263,497 (176)

Freely scalable and reconfigurable optical hardware for deep learning

Scientific Reports, 2021
As deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic processors are
Liane Bernstein, Alexander Sludds, Ryan Hamerly, Vivienne Sze, Joel Emer, Dirk Englund   +5 more
doaj   +1 more source

Lightcurve Classification in Massive Variability Surveys II: Transients towards the Large Magellanic Cloud

, 2004
Automatic classification of variability is now possible with tools like neural networks. Here, we present two neural networks for the identification of microlensing events -- the first discriminates against variable stars and the second against ...
Afonso, Afonso, Afonso, Alcock, Alcock, Alcock, Alcock, An, Antonello, Belokurov, Bennett, Bishop, Buchalter, Di Stefano, Dominik, Gould, Kerins, Lasserre, Lira, MacKay, MacKay, Mao, Mao, N. Wyn Evans, Nabney, Paczyński, Palanque-Delabrouille, Phillips, Press, Saerens, Vasily Belokurov, Welch, Yann Le Du   +32 more
core   +1 more source

Optical Design of a Smart-Pixel-Based Optical Convolutional Neural Network

Optics
We designed lens systems for a smart-pixel-based optical convolutional neural network (SPOCNN) using optical software to analyze image spread and estimate alignment tolerance for various kernel sizes.
Young-Gu Ju
doaj   +1 more source

Deep Learning Reconstruction of Ultra-Short Pulses

, 2018
Ultra-short laser pulses with femtosecond to attosecond pulse duration are the shortest systematic events humans can create. Characterization (amplitude and phase) of these pulses is a key ingredient in ultrafast science, e.g., exploring chemical ...
Cohen, Oren, Dikopoltsev, Alex, Mannor, Shie, Segev, Mordechai, Zahavy, Tom   +4 more
core   +1 more source

Learning to Extract Motion from Videos in Convolutional Neural Networks

, 2016
This paper shows how to extract dense optical flow from videos with a convolutional neural network (CNN). The proposed model constitutes a potential building block for deeper architectures to allow using motion without resorting to an external algorithm,
BKP Horn, D Fleet, D Fortun, DJ Butler, DJ Heeger, EH Adelson, F Solari, GW Taylor, KG Derpanis, KG Derpanis, NC Rust, T Brox, T Brox, V Ulman, YA LeCun   +14 more
core   +1 more source

Intelligent optical performance monitor using multi-task learning based artificial neural network

, 2018
An intelligent optical performance monitor using multi-task learning based artificial neural network (MTL-ANN) is designed for simultaneous OSNR monitoring and modulation format identification (MFI).
Shu, * Liang, Wan, Zhiquan, Xu, Kun, Yu, Zhenming, Zhang, Haojie, Zhao, Yilun   +5 more
core   +1 more source

Incoherent Optical Neural Networks for Passive and Delay-Free Inference in Natural Light

Photonics
Optical neural networks are hardware neural networks implemented based on physical optics, and they have demonstrated advantages of high speed, low energy consumption, and resistance to electromagnetic interference in the field of image processing ...
Rui Chen, Yijun Ma, Zhong Wang, Shengli Sun   +3 more
doaj   +1 more source

Vertically hierarchical electro-photonic neural network by cascading element-wise multiplication

APL Photonics
Integrated photonic neural networks (PNNs) usually adopt traditional convolutional neural network (CNN) or multilayer perceptron (MLP) network models.
Guangwei Cong, Noritsugu Yamamoto, Rai Kou, Yuriko Maegami, Shu Namiki, Koji Yamada   +5 more
doaj   +1 more source

Optical Lensless-Camera Communications Aided by Neural Network

Applied Sciences, 2019
Currently, the optical components of a camera embedded in the device constrain its overall thickness. Moreover, if the camera is strongly shaken, the lens and sensor may be misaligned, resulting in a defocusing effect.
Suhua Zhong, Yuhong Zhu, Xuefen Chi, Hanyang Shi, Hongliang Sun, Shuang Wang   +5 more
doaj   +1 more source

Scaling up for end-to-end on-chip photonic neural network inference

Light: Science & Applications
Optical neural networks are emerging as a competitive alternative to their electronic counterparts, offering distinct advantages in bandwidth and energy efficiency.
Bo Wu, Chaoran Huang, Jialong Zhang, Hailong Zhou, Yilun Wang, Jianji Dong, Xinliang Zhang   +6 more
doaj   +1 more source