Results 261 to 270 of about 907,184 (299)

Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization

Advances in Computational Mathematics, 2006
Solutions of learning problems by Empirical Risk Minimization (ERM) – and almost-ERM when the minimizer does not exist – need to be consistent, so that they may be predictive. They also need to be well-posed in the sense of being stable, so that they might be used robustly.
Sayan Mukherjee, Partha Niyogi, Tomaso Poggio, Ryan Rifkin   +3 more
openalex   +3 more sources

On a unique solution and stability analysis of a class of stochastic functional equations arising in learning theory

Analysis, 2022
Abstract Numerous computational and learning theory models have been studied using probabilistic functional equations. Especially in two-choice scenarios, the vast bulk of animal behavior research divides such situations into two different events. They split these actions into two possibilities according to the animals’ progress toward a
Ali Turab
openalex   +2 more sources

Further results on dynamic iterative learning control law design using repetitive process stability theory

2017 10th International Workshop on Multidimensional (nD) Systems (nDS), 2017
Iterative learning control can be applied to systems that execute the same finite duration task over and over again. This method control has been applied to many engineering systems, such as gantry robots and electrical motors. This paper gives further results on the design of dynamic iterative learning control laws using the repetitive process setting
Łukasz Hładowski, Krzysztof Gałkowski, Eric Rogers   +2 more
openalex   +3 more sources

Improvement of Power Systems Stability Using a New Learning Algorithm Based on Lyapunov Theory for Neural Network

Iranian Journal of Science and Technology, Transactions of Electrical Engineering, 2017
In this paper, a new learning algorithm based on Lyapunov stability theory for neural networks is used to improve the power system stability. During the online control process, the identification of system is not necessary, because of learning ability of the proposed controller.
Mehdi Arab Sadegh, Mohsen Farahani
openalex   +3 more sources

Some of the next articles are maybe not open access.

Related searches:

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
openaire   +2 more sources

Reliability Evaluation Method of Power Grid Security and Stability Control System Based on Survival Theory and Deep Learning

2021 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia), 2021
Weiwei Cai, Yuxin Shi, Weiheng Han, Lijia Ren, Ting Lei, Hourui Liu, Jingchi Xie, Sheng Huang   +7 more
openalex   +2 more sources

Deep Lyapunov Learning: Embedding the Lyapunov Stability Theory in Interpretable Neural Networks for Transient Stability Assessment

IEEE Transactions on Power Systems
Jiacheng Liu, Jun Liu, Rudai Yan, Tao Ding   +3 more
openalex   +2 more sources

Static Voltage Stability Margin Evaluation Considering Stochastic Power Injection Based on Deep Reinforcement Learning Theory

2022 IEEE 5th International Electrical and Energy Conference (CIEEC), 2022
Yi Yun Tian, Jun Yi Zhang, Wen Huang, Ceng Lin Ruan, Yi Chao Wu, Li Xia Sun   +5 more
openalex   +2 more sources

A Test Oracle for Reinforcement Learning Software Based on Lyapunov Stability Control Theory

2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)
Shiyu Zhang, Haoyang Song, Qixin Wang, Henghua Shen, Yu Pei   +4 more
openalex   +2 more sources

Predicting the Thermodynamic Stability of Solids Combining Density Functional Theory and Machine Learning

Chemistry of Materials, 2017
We perform a large scale benchmark of machine learning methods for the prediction of the thermodynamic stability of solids. We start by constructing a data set that comprises density functional theory calculations of around 250000 cubic perovskite systems.
Jonathan Schmidt, Jingming Shi, Pedro Borlido, Liming Chen, Silvana Botti, Miguel A. L. Marques   +5 more
openaire   +2 more sources