Research talks: Few-shot and zero-shot visual learning and reasoning

621
34.5
Опубликовано 8 февраля 2022, 17:56
Speakers:
Kyoung Mu Lee, Professor, Seoul National University
Han Hu, Principal Researcher, Microsoft Research Asia
Zhe Gan, Senior Researcher, Microsoft

Humans learn, infer, and reason by leveraging prior knowledge without necessarily observing a large number of examples. Visual learning and reasoning technologies, such as few-shot and zero-shot learning, aim to enable human-like learning and reasoning in artificial intelligence (AI) systems. Join Professor Kyoung Mu Lee from Seoul National University, Microsoft Principal Researcher Han Hu, and Microsoft Senior Researcher Zhe Gan as they discuss few-shot learning, zero-shot learning, and large-scale vision-and-language pre-training for reasoning. Gain a better understanding of the challenges and opportunities of these technologies.

Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
автотехномузыкадетское