Results 31 to 40 of about 406,491 (258)

Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition

, 2018
Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters.
Chen, Di, Chu, Xinqi, Li, Guangxi, Wang, Linnan, Xu, Zenglin, Ye, Jinmian, Zhe, Shandian   +6 more
core   +1 more source

Review of the mathematical foundations of data fusion techniques in surface metrology [PDF]

, 2015
The recent proliferation of engineered surfaces, including freeform and structured surfaces, is challenging current metrology techniques. Measurement using multiple sensors has been proposed to achieve enhanced benefits, mainly in terms of spatial ...
Ai C, Barker R M, Boudjemaa R, De Boor C, D𝚤ez D C, Fabio R, GmbH W, Golub G H, Hansen C D, Hao C, Hemsley R, Inhull, ISO 25178-6, ISO 25178-604, ISO/DIS 25178-606, JDL, Jiang X, Kjer H M, Leica Microsystems, Low K-L, Mathworks, Raid I, Ramasamy S K, Rasmussen C E, Rasmussen C E, Schabenberger O, Schmit J, Seeger S, Shekhar S, Strutz T, Sun W, Wang J, Weisstein E W, Yamany S M, Yan-Mei C   +34 more
core   +1 more source

Reference Information Based Remote Sensing Image Reconstruction with Generalized Nonconvex Low-Rank Approximation

Remote Sensing, 2016
Because of the contradiction between the spatial and temporal resolution of remote sensing images (RSI) and quality loss in the process of acquisition, it is of great significance to reconstruct RSI in remote sensing applications.
Hongyang Lu, Jingbo Wei, Lizhe Wang, Peng Liu, Qiegen Liu, Yuhao Wang, Xiaohua Deng   +6 more
doaj   +1 more source

A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations

, 2018
Artificial neural networks (ANNs) have very successfully been used in numerical simulations for a series of computational problems ranging from image classification/image recognition, speech recognition, time series analysis, game intelligence, and ...
Grohs, Philipp, Hornung, Fabian, Jentzen, Arnulf, von Wurstemberger, Philippe   +3 more
core   +1 more source

Invisible Base Electrode Coordinates Approximation for Simultaneous SPECT and EEG Data Visualization

Measurement Science Review, 2014
This work was performed as part of a larger research concerning the feasibility of improving the localization of epileptic foci, as compared to the standard SPECT examination, by applying the technique of EEG mapping.
Kowalczyk L., Goszczynska H., Zalewska E., Bajera A., Krolicki L.   +4 more
doaj   +1 more source

Contour-Based Corner Detection and Classification by Using Mean Projection Transform

Sensors, 2014
Image corner detection is a fundamental task in computer vision. Many applications require reliable detectors to accurately detect corner points, commonly achieved by using image contour information.
Seyed Mostafa Mousavi Kahaki, Md Jan Nordin, Amir Hossein Ashtari   +2 more
doaj   +1 more source

Optical distortion correction considering radial and tangential distortion rates defined by optical design

Results in Optics, 2021
This paper proposes a high-accuracy distortion correction method for optical imaging distortion mapping and computational image predistortion. Due to the establishment of the predistortion is based on the distortion evaluation in the common optical ...
Yue Liu, Dewen Cheng, Qiwei Wang, Qichao Hou, Luo Gu, Hailong Chen, Tong Yang, YongTian Wang   +7 more
doaj   +1 more source

Domain Specific Approximation for Object Detection

, 2018
There is growing interest in object detection in advanced driver assistance systems and autonomous robots and vehicles. To enable such innovative systems, we need faster object detection.
Chin, Ting-Wu, Genc, Hasan, Halpern, Matthew, Reddi, Vijay Janapa, Tsao, Shiao-Li, Yu, Chia-Lin   +5 more
core   +1 more source

FPGA-Based Implementation of Stochastic Configuration Network for Robotic Grasping Recognition

IEEE Access, 2020
Precise and rapid grasping recognition based on machine vision is one of the challenging problems for intelligent robots. As a nonlinear network for recognition, the stochastic configuration network (SCN) is considered as a promising method due to its ...
Jiaqi Pan, Feng Luan, Yunqi Gao, Yangjie Wei   +3 more
doaj   +1 more source

Deep Structured Features for Semantic Segmentation

, 2017
We propose a highly structured neural network architecture for semantic segmentation with an extremely small model size, suitable for low-power embedded and mobile platforms.
Benini, Luca, Cavigelli, Lukas, Mentzer, Fabian, Tschannen, Michael, Wiatowski, Thomas   +4 more
core   +1 more source