Research talk: Computationally efficient large-scale AI

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=0A5Gfm1Zu5o


Duration: 20:12
176 views
0

Speaker: Song Han, Assistant Professor, MIT

Today’s AI is too big. Deep neural networks demand extraordinary levels of computation, and therefore power and carbon, for training and inference. In this research talk, Song Han, MIT, presents TinyML and efficient deep learning techniques that make AI greener, smaller, faster, and deployable on IoT devices.

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



Other Videos By Microsoft Research


2022-02-08Research talk: Prompt tuning: What works and what's next
2022-02-08Closing remarks: Research for Carbon Negative
2022-02-08Research talks: Research partners on innovation for carbon neutralization
2022-02-08Panel: Innovative solutions and frontier technology for carbon neutralization from different angles
2022-02-08Research talk: Nexus between climate change and energy policy: Lessons from California
2022-02-08Research talk: Sustainable energy for all and the role of innovation
2022-02-08Research talk: When climate is everything, all systems must change
2022-02-08Research talk: Getting to net zero safely
2022-02-08Keynote: Building a net-zero future together
2022-02-08Opening Remarks: Research for Carbon Negative
2022-02-08Research talk: Computationally efficient large-scale AI
2022-02-08Research talk: Towards data-efficient machine learning with meta-learning
2022-02-08Research talk: Resource-efficient learning for large pretrained models
2022-02-08Research talk: Transformer efficiency: From model compression to training acceleration
2022-02-08Plenary: Industrial Research in the 21st Century
2022-02-02Dead-end Discovery: How offline reinforcement learning could assist healthcare decision-makers
2022-01-27Microsoft Soundscape - overview of Routes feature
2022-01-24Research talk: Breaking the deadly triad with a target network
2022-01-24Research talk: Learning and pretraining strategies for dense retrieval in search and beyond
2022-01-24Opening remarks: Research for Industry
2022-01-24Opening remarks: Future of Cloud Networking


Tags:
deep learning
large-scale models
large-scale AI models
AI
artificial intelligence
microsoft research summit