Results 271 to 280 of about 2,818,371 (325)

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

International Conference on Machine Learning, 2023
Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate whether a model faithfully followed instructions or generated safe outputs ...
Collin Burns, Pavel Izmailov, J. Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas R. Joglekar, Jan Leike, I. Sutskever, Jeff Wu, OpenAI   +12 more
semanticscholar   +1 more source

SLIP: Self-supervision meets Language-Image Pre-training

European Conference on Computer Vision, 2021
Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. CLIP, an exciting new approach to learning with language supervision, demonstrates promising performance on a ...
Norman Mu, Alexander Kirillov, David A. Wagner, Saining Xie   +3 more
semanticscholar   +1 more source

Prototype Augmentation and Self-Supervision for Incremental Learning

Computer Vision and Pattern Recognition, 2021
Despite the impressive performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning new tasks incrementally.
Fei Zhu, Xu-Yao Zhang, Chuan Wang, Fei Yin, Cheng-Lin Liu   +4 more
semanticscholar   +1 more source

Supervised learning

American Journal of Orthodontics and Dentofacial Orthopedics, 2023
This research received funding from the Flemish Government under the “Onderzoeksprogramma Artifici€ele Intelligentie (AI) Vlaanderen ...
Dirk Valkenborg, Melvin Geubbelmans, Axel-Jan Rousseau, Tomasz Burzykowski   +3 more
openaire   +3 more sources

Abusive Supervision

Oxford Research Encyclopedia of Business and Management, 2019
In recent years scholars of abusive supervision have expanded the scope of outcomes examined and have advanced new psychological and social processes to account for these and other outcomes.
A. Peng, R. Mitchell, J. Schaubroeck
semanticscholar   +1 more source