Results 21 to 30 of about 36,010,976 (311)
Convolutional neural networks with fractional order gradient method [PDF]
Neurocomputing, 2019 This paper proposes a fractional order gradient method for the backward propagation of convolutional neural networks. To overcome the problem that fractional order gradient method cannot converge to real extreme point, a simplified fractional order ...
Dian Sheng +3 more
semanticscholar +1 more source
A Double-Neighborhood Gradient Method for Infrared Small Target Detection
IEEE Geoscience and Remote Sensing Letters, 2020 Effective and efficient infrared (IR) small target detection is essential for IR search and tracking (IRST) systems. The current methods have some limitations in background suppression or detection of targets close to each other. In this letter, a double-
Lang Wu +4 more
semanticscholar +1 more source
A Push-Pull Gradient Method for Distributed Optimization in Networks [PDF]
IEEE Conference on Decision and Control, 2018 In this paper, we focus on solving a distributed convex optimization problem in a network, where each agent has its own convex cost function and the goal is to minimize the sum of the agents' cost functions while obeying the network connectivity ...
Shi Pu, Wei Shi, Jinming Xu, A. Nedić
semanticscholar +1 more source
A Decentralized Proximal-Gradient Method With Network Independent Step-Sizes and Separated Convergence Rates [PDF]
IEEE Transactions on Signal Processing, 2017 This paper proposes a novel proximal-gradient algorithm for a decentralized optimization problem with a composite objective containing smooth and nonsmooth terms.
Zhi Li, W. Shi, Ming Yan
semanticscholar +1 more source
Компьютерная оптика, 2023 We consider a gradient method for calculating cascaded diffractive optical elements (DOEs) consisting of several sequentially placed phase DOEs. Using the unitarity property of the operator describing the light propagation through the cascaded DOE, we ...
D.V. Soshnikov +2 more
doaj +1 more source
Reducing computational costs in deep learning on almost linearly separable training data [PDF]
Компьютерная оптика, 2020 Previous research in deep learning indicates that iterations of the gradient descent, over separable data converge toward the L2 maximum margin solution.
Ilona Kulikovskikh
doaj +1 more source
Exact Worst-Case Convergence Rates of the Proximal Gradient Method for Composite Convex Minimization [PDF]
Journal of Optimization Theory and Applications, 2017 We study the worst-case convergence rates of the proximal gradient method for minimizing the sum of a smooth strongly convex function and a non-smooth convex function, whose proximal operator is available.
Adrien B. Taylor +2 more
semanticscholar +1 more source
Incentive Price-Based Demand Response in Active Distribution Grids
Applied Sciences, 2020 Integration of PV power generation systems at distribution grids, especially at low-voltage (LV) grids, brings in operational challenges for distribution system operators (DSOs).
Karthikeyan Nainar +2 more
doaj +1 more source
Generalization of the gradient method with fractional order gradient direction [PDF]
Journal of the Franklin Institute, 2018 This paper focuses on the fractional difference of Lyapunov functions related to Riemann-Liouville, Caputo and Grünwald-Letnikov definitions. A new way of building Lyapunov functions is introduced and then five inequalities are derived for each ...
Yiheng Wei +3 more
semanticscholar +1 more source
Analysis and Synthesis in the Design of Magnetic Switching Electric Machines
Actuators, 2021 A systematic approach to the design of electrical machines is implemented by solving problems of analysis and synthesis in various combinations at different stages and stages of design. The questions of the formulation and implementation of synthesis and
Nikolay Shaitor +2 more
doaj +1 more source