Results 81 to 90 of about 298,507 (214)

Spatiotemporal diffractive deep neural networks

Optics Express
A spatiotemporal diffractive deep neural network (STD2NN) is proposed for spatiotemporal signal processing. The STD2NN is formed by gratings, which convert the signal from the frequency domain to the spatial domain, and multiple layers consisting of spatial lenses and space light modulators (SLMs), which conduct spatiotemporal phase modulation.
Junhe Zhou, Haoqian Pu, Jiaxin Yan
openaire   +2 more sources

Deep Pyramid Convolutional Neural Networks for Text Categorization [PDF]

, 2017
Rie Johnson, Tong Zhang
openalex   +1 more source

Spatial deep convolutional neural networks

Spatial Statistics
Spatial prediction problems often use Gaussian process models, which can be computationally burdensome in high dimensions. Specification of an appropriate covariance function for the model can be challenging when complex non-stationarities exist. Recent work has shown that pre-computed spatial basis functions and a feed-forward neural network can ...
Qi Wang, Paul A. Parker, Robert Lund
openaire   +3 more sources

Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks [PDF]

, 2017
Huei‐Fang Yang, Kevin Lin, Chu‐Song Chen   +2 more
openalex   +1 more source

Deep Convolutional Neural Network With Adversarial Training for Denoising Digital Breast Tomosynthesis Images

, 2021
Mingjie Gao, Jeffrey A. Fessler, Heang‐Ping Chan   +2 more
openalex   +2 more sources

Deep Multi-Component Neural Network Architecture

Computation
Existing neural network architectures often struggle with two critical limitations: (1) information loss during dataset length standardization, where variable-length samples are forced into fixed dimensions, and (2) inefficient feature selection in ...
Chafik Boulealam, Hajar Filali, Jamal Riffi, Adnane Mohamed Mahraz, Hamid Tairi   +4 more
doaj   +1 more source

AcousticIA, a deep neural network for multi-species fish detection using multiple models of acoustic cameras

, 2023
Guglielmo Fernandez Garcia, Thomas Corpetti, Marie Nevoux, Laurent Beaulaton, François Martignac   +4 more
openalex   +2 more sources

Visualizing Transform Relations of Multilayers in Deep Neural Networks for ISAR Target Recognition [PDF]

, 2022
Jiaming Liu, Mengdao Xing, Wangshuo Tang, Changhong Chen   +3 more
openalex   +1 more source

ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining [PDF]

, 2019
Vojtěch Mrázek, Zdeněk Vašíček, Lukáš Sekanina, Muhammad Abdullah Hanif, Muhammad Shafique   +4 more
openalex   +1 more source

Enhancing deep neural network training efficiency and performance through linear prediction

Scientific Reports
Deep neural networks have achieved remarkable success in various fields. However, training an effective deep neural network still poses challenges. This paper aims to propose a method to optimize the training effectiveness of deep neural networks, with ...
Hejie Ying, Mengmeng Song, Yaohong Tang, Shungen Xiao, Zimin Xiao   +4 more
doaj   +1 more source