Results 21 to 30 of about 18,405,059 (322)
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation [PDF]
International Joint Conference on Artificial Intelligence, 2021 Knowledge distillation (KD), transferring knowledge from a cumbersome teacher model to a lightweight student model, has been investigated to design efficient neural architectures.
Taehyeon Kim +4 more
semanticscholar +1 more source
Cogent Engineering, 2021 In this study, proximate analysis and characterization techniques were carried out on maize tassel fibers immobilized with Polyvinyl Alcohol (PVA) for its usability as a biosorbent for adsorption process.
Muibat Diekola Yahya +4 more
doaj +1 more source
Guaranteed Performance of Nonlinear Attitude Filters on the Special Orthogonal Group SO(3)
IEEE Access, 2019 This paper proposes two novel nonlinear attitude filters evolved directly on the special orthogonal group $\mathbb {SO}\left ({3}\right)$ , able to ensure prescribed measures of transient and steady-state performance.
Hashim A. Hashim +2 more
doaj +1 more source
Asymptotic Expansions for Moench’s Integral Transform of Hydrology
Mathematics, 2023 Theis’ theory (1935), later improved by Hantush & Jacob (1955) and Moench (1971), is a technique designed to study the water level in aquifers. The key formula in this theory is a certain integral transform H[g](r,t) of the pumping function g that ...
José L. López +2 more
doaj +1 more source
Solving optimal control problems of the time-delayed systems by a neural network framework
Connection Science, 2019 A numerical method using neural networks for solving time-delayed optimal control problems is studied. The problem is first transformed into one without a time-delayed argument, using a Páde approximation.
Alireza Nazemi +2 more
doaj +1 more source
An a posteriori error estimate for Symplectic Euler approximation of optimal control problems [PDF]
, 2014 This work focuses on numerical solutions of optimal control problems. A time discretization error representation is derived for the approximation of the associated value function. It concerns Symplectic Euler solutions of the Hamiltonian system connected
Karlsson, Jesper +4 more
core +2 more sources
Importance Sampling for Objetive Funtion Estimations in Neural Detector Traing Driven by Genetic Algorithms [PDF]
, 2010 To train Neural Networks (NNs) in a supervised way, estimations of an objective function must be carried out. The value of this function decreases as the training progresses and so, the number of test observations necessary for an accurate estimation has
C Andrieu +29 more
core +2 more sources
Journal of Engineered Fibers and Fabrics, 2019 In order to find a simple and reliable method for the calculation of the diffusion coefficient, the correlation equation of concentration and distance in the form of complementary error function was derived from solving an ordinary differential equation ...
G. Park
semanticscholar +1 more source
Overview of intelligent optimization algorithm design of FIR digital filter
Dianzi Jishu Yingyong, 2021 This article summarizes the intelligent optimization algorithm of finite impulse response digital filter(FIR). The main idea of optimization design is to transform the digital filter design problem into the error function minimization problem.
Zhang Shuyu, Wang Ting
doaj +1 more source
A new approach to adaptive fuzzy control: the controller output error method [PDF]
, 2002 The controller output error method (COEM) is introduced and applied to the design of adaptive fuzzy control systems. The method employs a gradient descent algorithm to minimize a cost function which is based on the error at the controller output.
Andersen, HC, Lotfi, A, Tsoi, AC
core +1 more source