scholarly journals Analysis of large-scale digital optical neural networks by Feynman diagrams

1999 ◽  
Author(s):  
Jose A. Martin-Pereda ◽  
Ana P. Gonzalez-Marcos
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Feynman Diagrams ◽  
Optical Neural Networks

scholarly journals Large-Scale and Energy-Efficient Tensorized Optical Neural Networks on III-V-on-Silicon MOSCAP Platform

APL Photonics ◽  
2021 ◽  
Author(s):  
Xian Xiao ◽  
Mehmet Berkay On ◽  
Thomas Van Vaerenbergh ◽  
Di Liang ◽  
Ray Beausoleil ◽  
...  
Keyword(s):  
Neural Networks ◽  
Energy Efficient ◽  
Large Scale ◽  
Optical Neural Networks

scholarly journals Implementation of Pruned Backpropagation Neural Network Based on Photonic Integrated Circuits

Photonics ◽  
2021 ◽  
Vol 8 (9) ◽  
pp. 363
Author(s):  
Qi Zhang ◽  
Zhuangzhuang Xing ◽  
Duan Huang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Integrated Circuits ◽  
Energy Efficient ◽  
High Speed ◽  
Large Scale ◽  
Matrix Operation ◽  
Optical Neural Networks ◽  
Optical Neural Network ◽  
Random Initialization

We demonstrate a pruned high-speed and energy-efficient optical backpropagation (BP) neural network. The micro-ring resonator (MRR) banks, as the core of the weight matrix operation, are used for large-scale weighted summation. We find that tuning a pruned MRR weight banks model gives an equivalent performance in training with the model of random initialization. Results show that the overall accuracy of the optical neural network on the MNIST dataset is 93.49% after pruning six-layer MRR weight banks on the condition of low insertion loss. This work is scalable to much more complex networks, such as convolutional neural networks and recurrent neural networks, and provides a potential guide for truly large-scale optical neural networks.

Use of Feynman diagrams in large-scale neural networks with nonlinear behavior

1993 ◽  
Author(s):  
Jose A. Martin-Pereda ◽  
Ana P. Gonzalez-Marcos
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Nonlinear Behavior ◽  
Feynman Diagrams

scholarly journals Large-Scale Optical Neural Networks Based on Photoelectric Multiplication

2019 ◽  
Vol 9 (2) ◽  
Author(s):  
Ryan Hamerly ◽  
Liane Bernstein ◽  
Alexander Sludds ◽  
Marin Soljačić ◽  
Dirk Englund
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Optical Neural Networks

scholarly journals Digital Optical Neural Networks for Large-Scale Machine Learning

2020 ◽  
Author(s):  
Liane Bernstein ◽  
Alexander Sludds ◽  
Ryan Hamerly ◽  
Vivienne Sze ◽  
Joel Emer ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Large Scale ◽  
Optical Neural Networks

Financial Market Prediction and Improving the Performance Based on Large-scale Exogenous Variables and Deep Neural Networks

2020 ◽  
Vol 9 (4) ◽  
pp. 26-35
Author(s):  
Sung Gil Cheon ◽  
Ju Hong Lee ◽  
Bum Ghi Choi ◽  
Jae Won Song
Keyword(s):  
Neural Networks ◽  
Financial Market ◽  
Large Scale ◽  
Deep Neural Networks ◽  
Exogenous Variables

A Developmental Method for Evolving Large-Scale Spiking Neural Networks

2012 ◽  
Vol 35 (12) ◽  
pp. 2633 ◽  
Author(s):  
Xiang-Hong LIN ◽  
Tian-Wen ZHANG ◽  
Gui-Cang ZHANG
Keyword(s):  
Neural Networks ◽  
Large Scale ◽  
Spiking Neural Networks

Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home

2017 ◽  
Author(s):  
Chanwoo Kim ◽  
Ananya Misra ◽  
Kean Chin ◽  
Thad Hughes ◽  
Arun Narayanan ◽  
...  
Keyword(s):  
Neural Networks ◽  
Speech Recognition ◽  
Large Scale ◽  
Deep Neural Networks ◽  
Far Field

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

Sign in / Sign up

Export Citation Format

Share Document