Colloquium
- Mason Porter; Department of Mathematics; University of California, Los Angeles (UCLA)Opinion Dynamics on NetworksFrom the spreading of diseases and memes to the development ofopinions and social influence, dynamical processes are influenced
- Matthew Peters, Senior Research Scientist, Allen Institute for Artificial IntelligenceA guided tour of contextual word representations for language understandingThe last 3-4 years have seen a tremendous increase in the abilities of natural language
- Abdelrahman Mohamed, Research Scientist, Facebook AI ResearchRecent advances in speech representation learningSelf-supervised representation learning methods recently achieved great successes in NLP and computer vision domains, reaching new
- Pieter Abbeel; Professor of Electrical Engineering and Computer Science; University of California, BerkeleyUnsupervised Reinforcement LearningDeep reinforcement learning (Deep RL) has seen many successes, including learning to play Atari games, the
- Abdelrahman Mohamed, Research Scientist, Facebook AI ResearchRecent advances in speech representation learningSelf-supervised representation learning methods recently achieved great successes in NLP and computer vision domains, reaching new
- Mihaela van der Schaar, John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine, University of Cambridge; Turing Fellow, The Alan Turing Institute in London; Chancellor’s Professor, UCLAWhy medicine is creating
- Oriol Vinyals, Research Scientist, Google DeepMindAlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning Games have been used for decades as an important way to test and evaluate the performance of artificial
- Yanping Huang, Staff Software Engineer, Google BrainGShard: Scaling Giant Models with Conditional Computation and Automatic Sharding Neural network scaling has been critical for improving the model quality in many real-world machine
- Fausto Milletari, Lead of Applied AI, Johnson and JohnsonVolumetric medical image processing with deep learning One of the fundamental capabilities of deep learning is its ability of accomplishing a multitude of tasks by learning features
- Andrey Zhmoginov, Research Software Engineer, Google AIImage understanding and image-to-image translation through the lens of information loss The computation performed by a deep neural network is typically composed of multiple processing stages