Results 101 to 110 of about 786,949 (131)
STABILITY RESULTS IN LEARNING THEORY [PDF]
Analysis and Applications, 2005 The problem of proving generalization bounds for the performance of learning algorithms can be formulated as a problem of bounding the bias and variance of estimators of the expected error. We show how various stability assumptions can be employed for this purpose.
Alexander Rakhlin +2 more
openalex +2 more sources
Stability theory of universal learning network
1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929), 2002 Higher order derivatives of the universal learning network (ULN) has been previously derived by forward and backward propagation computing methods, which can model and control the large scale complicated systems such as industrial plants, economic, social and life phenomena. In this paper, a new concept of nth order asymptotic orbital stability for the
Kotaro Hirasawa +3 more
openalex +3 more sources
Stability Certificates for Neural Network Learning-based Controllers using Robust Control Theory
2021 American Control Conference (ACC), 2021 Providing stability guarantees for controllers that use neural networks can be challenging. Robust control theoretic tools are used to derive a framework for providing nominal stability guarantees – stability guarantees for a known nominal system – controlled by a learning-based neural network controller.
Nguyen Hoang Hai +5 more
openalex +3 more sources
Analysis of robust control using stability theory of universal learning networks
IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028), 2003 Nth order asymptotic orbital stability analysis method has been proposed to determine whether a nonlinear system is stable or not with large fluctuations of the system states. In this paper, we discuss the stability of robust control of a nonlinear crane system using this method.
Yunqing Yu +3 more
openalex +3 more sources
The Journal of Chemical Physics, 2018 We use a combination of machine learning techniques and high-throughput density-functional theory calculations to explore ternary compounds with the AB2C2 composition. We chose the two most common intermetallic prototypes for this composition, namely, the tI10-CeAl2Ga2 and the tP10-FeMo2B2 structures.
Jonathan Schmidt +3 more
openalex +4 more sources
Principled reward shaping for reinforcement learning via lyapunov stability theory
Neurocomputing, 2020 Abstract Reinforcement learning (RL) suffers from the designation in reward function and the large computational iterating steps until convergence. How to accelerate the training process in RL plays a vital role. In this paper, we proposed a Lyapunov function based approach to shape the reward function which can effectively accelerate the training ...
Yunlong Dong, Xiuchuan Tang, Ye Yuan
openalex +3 more sources
2011 IEEE International Symposium on Intelligent Control, 2011 This paper considers iterative learning control for the practically relevant case of deterministic discrete linear plants where the first Markov parameter is zero. A 2D systems approach that uses a strong form of stability for linear repetitive processes is used to develop a one step control law design for both trial-to-trial error convergence and ...
Łukasz Hładowski +5 more
openalex +3 more sources
Physical Chemistry Chemical Physics, 2022 Composition, size, and structure dependences of stable configuration of Pd–Ru alloy nanoparticles under finite temperature were theoretically investigated by using density functional theory calculation, multiple regression, and Wang–Landau sampling.
Yūsuke Nanba, Michihisa Koyama
openalex +3 more sources
Experimentally verified Iterative Learning Control based on repetitive process stability theory
2012 American Control Conference (ACC), 2012 This paper gives new results on the design and experimental evaluation of an Iterative Learning Control (ILC) law in a repetitive process setting. The experimental results given are from a gantry robot facility that has been extensively used in the benchmarking of linear model based ILC designs.
Dabkowski +7 more
+5 more sources
2016 IEEE 55th Conference on Decision and Control (CDC), 2016 Iterative learning control laws can be applied to systems that execute the same finite duration task over and over again. Previous research for linear dynamics has used the stability theory of linear repetitive processes to design control laws that have been experimentally verified.
Pavel Pakshin +4 more
openalex +3 more sources