Research talks: Generalization and adaptation

Channel:
Microsoft Research
Subscribers:
351,000
Published on ● Video Link: https://www.youtube.com/watch?v=lfPSlrTotf4


Duration: 29:55
229 views
1

Speakers:
Suha Kwak, Professor, POSTECH
Chong Luo, Principal Researcher, Microsoft Research Asia
Lu Yuan, Principal Research Manager, Microsoft

The limitations of big data-driven deep learning in scalability and adaptation to real-world scenarios hinder its practical applications. To address these limitations, it’s extremely important to develop architectures and algorithms that can capture the fundamentals of how humans learn, infer, and reason. Join Professor Suha Kwak from POSTECH, Microsoft Principal Researcher Chong Luo, and Microsoft Principal Research Manager Lu Yuan as they discuss the theory and practice of unsupervised visual representation learning for 3D point clouds, videos, and images, which help address model generalization and adaptation to new data domains and new downstream tasks.

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



Other Videos By Microsoft Research


2022-02-24Towards a New Biology Nexus: Race, Society and Story in the Science of Life
2022-02-18Microsoft Soundscape - an Illustrated Demonstration
2022-02-08Research talk: Maia Chess: A human-like neural network chess engine
2022-02-08Research talk: Safe reinforcement learning using advantage-based intervention
2022-02-08Research talk: Reinforcement learning with preference feedback
2022-02-08Keynote: Key research challenges for real world reinforcement learning
2022-02-08Opening remarks: Reinforcement Learning
2022-02-08Closing remarks: Health & Life Sciences - Discovery
2022-02-08Keynote: ReduNet: Deep (convolutional) networks from the principle of rate reduction
2022-02-08Closing remarks: Towards Human-Like Visual Learning and Reasoning
2022-02-08Research talks: Generalization and adaptation
2022-02-08Research talk: CitizenEndo: Patient-centered endometriosis research
2022-02-08Research talks: Few-shot and zero-shot visual learning and reasoning
2022-02-08Research talk: Learning to read the adaptive immune systems of humans
2022-02-08Research talk: Next generation spatial genomics
2022-02-08Research talk: Leveraging uncertainty in machine learning to bridge computation and experimentation
2022-02-08Research talks: Learning for interpretability
2022-02-08Fireside chat: The future of medicines and innovation
2022-02-08Keynote: Learning from observation: Small-data approach to human common sense
2022-02-08Fireside chat: Emergent innovation
2022-02-08Tutorial: Accelerating research with the InnerEye medical imaging toolbox and Azure machine learning


Tags:
Human-Like Visual Learning
visual learning
visual Reasoning
big data deep learning
visual tasks
real-world tasks
microsoft research summit