Seminars

Joint APPM/PHYS Colloquium - Philip Stark

Feb. 24, 2021

Philip Stark; Department of Statistics; University of California, Berkeley Evidence-Based Elections Elections rely on people, hardware, and software, all of which are fallible and subject to manipulation. Well resourced nation-states continue to attack U.S. elections. Voting equipment is built by private vendors–some foreign, but all using foreign parts. Many states...

APPM Department Colloquium - Jeffrey Pennington

Feb. 19, 2021

Jeffrey Pennington, Research Scientist, Google Brain Demystifying deep learning through high-dimensional statistics As deep learning continues to amass ever more practical success, its novelty has slowly faded, but a sense of mystery persists and we still lack satisfying explanations for how and why these models perform so well. Among the...

APPM Department Colloquium - Esteban Real

Feb. 12, 2021

Esteban Real, Software Engineer, Google Brain Evolving Machine Learning Algorithms The effort devoted to hand-crafting machine learning (ML) models has motivated the use of automated methods. These methods, collectively known as AutoML, can today optimize the models' architectures to surpass the performance of manual designs. I will discuss how evolutionary...

APPM Department Colloquium - Christian Szegedy

Feb. 5, 2021

Christian Szegedy, Staff Research Scientist, Google Machine 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-order and higher-order logic. After a short introduction of the type of problems addressed and the general...

APPM Department Colloquium - Rico Sennrich

Jan. 29, 2021

Rico Sennrich, Professor of Computational Linguistics, University of Zurich Lessons from Multilingual Machine Translation Neural models have brought rapid advances to the field of machine translation, and have also opened up new opportunities. One of these is the training of machine translation models in two or more translation directions to...

APPM Department Colloquium - Rob Fergus

Jan. 22, 2021

Rob Fergus, Professor of Computer Science, New York University and Research Scientist, DeepMind Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences In the field of artificial intelligence, a combination of scale in data and model capacity enabled by unsupervised learning has led to major...

APPM Department Colloquium - Susan Murphy

Dec. 4, 2020

Susan Murphy, Radcliffe Alumnae Professor at the Radcliffe Institute and Professor of Statistics and Computer Science, Harvard University Challenges in Developing Learning Algorithms to Personalize Treatment in Real Time There are a variety of formidable challenges to reinforcement learning and control for use in designing digital health interventions for individuals...

APPM Department Colloquium Susan Murphy

Nov. 29, 2020

APPM Colloquium: Speaker : Susan Murphy Affiliations: Department of Statistics , Harvard University Department of Computer Science , Harvard University Radcliffe Institute for Advanced Study , Harvard University Day/Time: Friday, December 4th 2020, 4:10pm-5:10pm MST Location: Virtual talk on Zoom: https://cuboulder.zoom.us/j/95938791886 Talk Title: Challenges in Developing Learning Algorithms to Personalize...

APPM Department Colloquium - Alex Hening

Nov. 20, 2020

Alex Hening, Department of Mathematics, Tufts Universy The competitive exclusion principle in stochastic environments The competitive exclusion principle states in its simplest form that a number of species competing for a smaller number of resources cannot coexist. Nevertheless, in nature there are many instances where this is not true. One...

APPM Department Colloquium - Vrushali Bokil

Nov. 13, 2020

Vrushali Bokil, Department of Mathematics, Oregon State University Compatible Discretizations for Maxwell’s Equations in Complex Materials In this talk, we discuss the construction of a specific compatible discretization, the Mimetic Finite Difference (MFD) method, for time domain electromagnetic wave propagation in linear dispersive media. The discretization utilizes an optimization procedure...

Pages