Colloquium
- Dumitru Erhan, Staff Research Scientist and Tech Lead Manager, Google Brain Enabling world models via unsupervised representation learning of environments. In order to build intelligent agents that quickly adapt to new scenes,
- Mingxing Tan, Staff Software Engineer, Google BrainAutoML for Efficient Vision Learning This talk will focus on a few recent progresses we have made on AutoML, particularly on neural architecture search for efficient convolutional neural
- Kalesha Bullard, Postdoctoral Researcher, Facebook AI ResearchLearning through Interaction in Cooperative Multi-Agent SystemsEffective communication is an important skill for enabling information exchange and cooperation in multi-agent systems, in
- Philip Stark; Department of Statistics; University of California, BerkeleyEvidence-Based ElectionsElections rely on people, hardware, and software, all of which are fallible and subject to manipulation. Well resourced nation-states continue to
- Jeffrey Pennington, Research Scientist, Google BrainDemystifying deep learning through high-dimensional statisticsAs deep learning continues to amass ever more practical success, its novelty has slowly faded, but a sense of mystery persists and we
- Esteban Real, Software Engineer, Google BrainEvolving Machine Learning AlgorithmsThe effort devoted to hand-crafting machine learning (ML) models has motivated the use of automated methods. These methods, collectively known as AutoML, can today
- Christian Szegedy, Staff Research Scientist, GoogleMachine Learning for Mathematical Reasoning In this talk I will discuss the application of transformer based language models and graph neural networks on automated reasoning tasks in first-
- Rico Sennrich, Professor of Computational Linguistics, University of ZurichLessons from Multilingual Machine Translation Neural models have brought rapid advances to the field of machine translation, and have also opened up new
- Rob Fergus, Professor of Computer Science, New York University and Research Scientist, DeepMindBiological structure and function emerge from scaling unsupervised learning to 250 million protein sequences In the field of artificial
- Susan Murphy, Radcliffe Alumnae Professor at the Radcliffe Institute and Professor of Statistics and Computer Science, Harvard UniversityChallenges in Developing Learning Algorithms to Personalize Treatment in Real TimeThere are a variety of