Results 11 to 20 of about 977,116 (306)
Machine learning active-nematic hydrodynamics [PDF]
Proceedings of the National Academy of Sciences, 2021 Hydrodynamic theories effectively describe many-body systems out of equilibrium in terms of a few macroscopic parameters. However, such parameters are difficult to determine from microscopic information. Seldom is this challenge more apparent than in active matter, where the hydrodynamic parameters are in fact fields that encode the distribution of ...
Jonathan Colen +12 more
openaire +6 more sources
Universal activation function for machine learning [PDF]
Scientific Reports, 2021 AbstractThis article proposes a universal activation function (UAF) that achieves near optimal performance in quantification, classification, and reinforcement learning (RL) problems. For any given problem, the gradient descent algorithms are able to evolve the UAF to a suitable activation function by tuning the UAF’s parameters.
Brosnan Yuen +3 more
openaire +4 more sources
Machine learning forecasting of active nematics [PDF]
Soft Matter, 2021 Our model is unrolled to map an input orientation sequence (from time t-8 to t-1) to an output one (t,t + 1…) with trajectray tracing. Cyan labels are −1/2 defect while purple ones are +1/2.
Zhengyang Zhou +8 more
openaire +3 more sources
Machine Learning for Active Portfolio Management [PDF]
The Journal of Financial Data Science, 2021 Machine learning (ML) methods are attracting considerable attention among academics in the field of finance. However, it is commonly believed that ML has not transformed the asset management industry to the same extent as other sectors. This survey focuses on the ML methods and empirical results available in the literature that matter most for active ...
Bartram, S. M. +3 more
openaire +2 more sources
The Role of Active Learning in Modern Machine Learning [PDF]
Even though Active Learning (AL) is widely studied, it is rarely applied in contexts outside its own scientific literature. We posit that the reason for this is AL's high computational cost coupled with the comparatively small lifts it is typically able to generate in scenarios with few labeled points.
Thorben Werner +2 more
openalex +3 more sources
Machine learning of molecular properties: Locality and active learning [PDF]
The Journal of Chemical Physics, 2018 In recent years, the machine learning techniques have shown great potent1ial in various problems from a multitude of disciplines, including materials design and drug discovery. The high computational speed on the one hand and the accuracy comparable to that of density functional theory on another hand make machine learning algorithms efficient for high-
Konstantin Gubaev +2 more
openaire +3 more sources
A Comparative Analysis of Active Learning for Rumor Detection on Social Media Platforms
Applied Sciences, 2023 In recent years, the ubiquity of social networks has transformed them into essential platforms for information dissemination. However, the unmoderated nature of social networks and the advent of advanced machine learning techniques, including generative ...
Feng Yi +3 more
doaj +1 more source
A Review on Machine Learning Styles in Computer Vision—Techniques and Future Directions
IEEE Access, 2022 Computer applications have considerably shifted from single data processing to machine learning in recent years due to the accessibility and availability of massive volumes of data obtained through the internet and various sources.
Supriya V. Mahadevkar +6 more
doaj +1 more source
Human Gait Activity Recognition Machine Learning Methods
Sensors, 2023 Human gait activity recognition is an emerging field of motion analysis that can be applied in various application domains. One of the most attractive applications includes monitoring of gait disorder patients, tracking their disease progression and the modification/evaluation of drugs.
Jan Slemenšek +6 more
openaire +3 more sources
Learning to Actively Learn Neural Machine Translation [PDF]
Proceedings of the 22nd Conference on Computational Natural Language Learning, 2018 Traditional active learning (AL) methods for machine translation (MT) rely on heuristics. However, these heuristics are limited when the characteristics of the MT problem change due to e.g. the language pair or the amount of the initial bitext. In this paper, we present a framework to learn sentence selection strategies for neural MT.
Ming Liu +2 more
openaire +1 more source