Results 1 to 10 of about 16,611 (93)
Exploratory State Representation Learning [PDF]
Frontiers in Robotics and AI, 2022 Not having access to compact and meaningful representations is known to significantly increase the complexity of reinforcement learning (RL). For this reason, it can be useful to perform state representation learning (SRL) before tackling RL tasks ...
Astrid Merckling +3 more
doaj +4 more sources
Diffusion-Based Causal Representation Learning
EntropyCausal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause–effect estimation and the identification of efficient and safe interventions.
Amir Mohammad Karimi Mamaghan +4 more
doaj +7 more sources
Evaluation for Instructional Interaction Using Bipartite Network Representation Learning [PDF]
Jisuanji kexue yu tansuo, 2023 With the combination and development of “Internet plus Education”, online education has become an important teaching mode at present. Research shows that the interaction in online education provides effective help for learners.
WANG Xuecen, ZHANG Yu, ZHAO Changkuan, CHEN Mo, YU Ge
doaj +1 more source
Distributed Variational Representation Learning [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 The problem of distributed representation learning is one in which multiple sources of information X1,…, XK are processed separately so as to learn as much information as possible about some ground truth Y. We investigate this problem from information-theoretic grounds, through a generalization of Tishby's centralized Information Bottleneck (IB) method
Aguerri, Inaki Estella +1 more
openaire +3 more sources
Toward Causal Representation Learning [PDF]
Proceedings of the IEEE, 2021 ISSN:1558 ...
Bernhard Scholkopf +6 more
openaire +4 more sources
Using Proximity Graph Cut for Fast and Robust Instance-Based Classification in Large Datasets
Complexity, 2021 K-nearest neighbours (kNN) is a very popular instance-based classifier due to its simplicity and good empirical performance. However, large-scale datasets are a big problem for building fast and compact neighbourhood-based classifiers. This work presents
Stanislav Protasov, Adil Mehmood Khan
doaj +1 more source
Comprehensive machine learning based study of the chemical space of herbicides
Scientific Reports, 2021 Widespread use of herbicides results in the global increase in weed resistance. The rotational use of herbicides according to their modes of action (MoAs) and discovery of novel phytotoxic molecules are the two strategies used against the weed resistance.
Davor Oršolić +3 more
doaj +1 more source
Metaheuristics for the Minimum Time Cut Path Problem with Different Cutting and Sliding Speeds
Algorithms, 2021 The problem of efficiently cutting smaller two-dimensional pieces from a larger surface is recurrent in several manufacturing settings. This problem belongs to the domain of cutting and packing (C&P) problems.
Bonfim Amaro Junior +4 more
doaj +1 more source
Review and Chemoinformatic Analysis of Ferroptosis Modulators with a Focus on Natural Plant Products
Molecules, 2023 Ferroptosis is a regular cell death pathway that has been proposed as a suitable therapeutic target in cancer and neurodegenerative diseases. Since its definition in 2012, a few hundred ferroptosis modulators have been reported.
Višnja Stepanić +1 more
doaj +1 more source
Redox Active Molecules in Cancer Treatments
Molecules, 2023 Cancer is one of the leading causes of death worldwide, with nearly 10 million deaths in 2020 [...]
Višnja Stepanić +1 more
doaj +1 more source