Results 21 to 30 of about 1,466,211 (327)
Quantum Journal of Social Sciences and Humanities, 2022 The education model in the 21st century shall be learner-centered. Learners are expected to be independent to engage in self-directed learning with the integration of technological tools in developing necessary 21st century skills. However, the foundation of this education model shall not be neglected as positive emotion and motivation are the ...
Dennis Chan Paul Leong
openalex +3 more sources
Fairness in Federated Learning via Core-Stability [PDF]
Neural Information Processing Systems, 2022 Federated learning provides an effective paradigm to jointly optimize a model benefited from rich distributed data while protecting data privacy. Nonetheless, the heterogeneity nature of distributed data makes it challenging to define and ensure fairness
B. Chaudhury +4 more
semanticscholar +1 more source
Deep Active Learning with Noise Stability [PDF]
AAAI Conference on Artificial Intelligence, 2022 Uncertainty estimation for unlabeled data is crucial to active learning. With a deep neural network employed as the backbone model, the data selection process is highly challenging due to the potential over-confidence of the model inference.
Xingjian Li +6 more
semanticscholar +1 more source
Designing stable neural identifier based on Lyapunov method [PDF]
Journal of Artificial Intelligence and Data Mining, 2015 The stability of learning rate in neural network identifiers and controllers is one of the challenging issues which attracts great interest from researchers of neural networks.
F. Alibakhshi +3 more
doaj +1 more source
Nature Communications, 2023 Surface Pourbaix diagrams are critical to understanding the stability of nanomaterials in electrochemical environments. Their construction based on density functional theory is, however, prohibitively expensive for real-scale systems, such as several ...
Kihoon Bang +5 more
semanticscholar +1 more source
COVID-19: Data-Driven Mean-Field-Type Game Perspective
Games, 2020 In this article, a class of mean-field-type games with discrete-continuous state spaces is considered. We establish Bellman systems which provide sufficiency conditions for mean-field-type equilibria in state-and-mean-field-type feedback form.
Hamidou Tembine
doaj +1 more source
D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory [PDF]
International Conference on Learning Representations, 2023 Kohn-Sham Density Functional Theory (KS-DFT) has been traditionally solved by the Self-Consistent Field (SCF) method. Behind the SCF loop is the physics intuition of solving a system of non-interactive single-electron wave functions under an effective ...
Tianbo Li +8 more
semanticscholar +1 more source
Beyond generalization: a theory of robustness in machine learning
Synthese, 2023 The term robustness is ubiquitous in modern Machine Learning (ML). However, its meaning varies depending on context and community. Researchers either focus on narrow technical definitions, such as adversarial robustness, natural distribution shifts, and ...
Timo Freiesleben, Thomas Grote
semanticscholar +1 more source
Towards a Unified Theory of Learning and Information
Entropy, 2020 In this paper, we introduce the notion of “learning capacity” for algorithms that learn from data, which is analogous to the Shannon channel capacity for communication systems.
Ibrahim Alabdulmohsin
doaj +1 more source
Machine learned synthesizability predictions aided by density functional theory
Communications Materials, 2022 In data-driven approaches for materials discovery, it is essential to account for phase stability when predicting synthesizability. Here, by combining density functional theory calculations and machine learning, the authors predict the synthesizability ...
Andrew Lee +6 more
doaj +1 more source