Seminars

Upcoming Seminars

No upcoming events found.

Previous Seminars

On the foundations of computational mathematics, Smale’s 18th problem and the potential limits of AI

Wed, Jul 15, 2020, 12:00 pm

There is a profound optimism on the impact of deep learning (DL) and AI in the sciences with Geoffrey Hinton concluding that 'They should stop educating radiologists now'. However, DL has an Achilles heel: it is universally unstable so that small changes in the initial data can lead to large errors in the final result. This has been documented...

Speaker(s):

Trainability and accuracy of artificial neural networks

Wed, Jul 8, 2020, 12:00 pm

The methods and models of machine learning (ML) are rapidly becoming de facto tools for the analysis and interpretation of large data sets. Complex classification tasks such as speech and image recognition, automatic translation, decision making, etc. that were out of reach a decade ago are now routinely performed by computers with a high...

Speaker(s):

Towards a mathematical understanding of supervised learning: What we know and what we don't know

Wed, Jul 1, 2020, 12:00 pm

Two of the biggest puzzles in machine learning are: Why is it so successful and why is it quite fragile? This talk will present a framework for unraveling these puzzles from the perspective of approximating functions in high dimensions.

Speaker(s):

Reimagining Digitized Newspapers with Machine Learning

Fri, May 15, 2020, 11:30 am

The 16 million digitized historic newspaper pages within Chronicling America, a joint initiative by the Library of Congress and the NEH, represent an incredibly rich resource for a wide range of users. Historians, journalists, genealogists, students, and members of the American public explore...

Speaker(s):

Running and Analyzing Large-scale Psychology Experiments

Fri, Mar 6, 2020, 12:00 pm

Psychology has traditionally been a laboratory discipline, focused on small-scale experiments conducted in person. However, recent technological innovations have made it possible to collect far more data from far more people than ever before.

Speaker(s):

Preference Modeling with Context-Dependent Salient Features

Mon, Feb 24, 2020, 4:00 pm

This talk considers the preference modeling problem and addresses the fact that pairwise comparison data often reflects irrational choice, e.g. intransitivity. Our key observation is that two items compared in isolation from other items may be compared based on only a salient subset of features.

Speaker(s):

Massively Parallel Evolutionary Computation for Empowering Electoral Reform

Fri, Feb 21, 2020, 12:15 pm
Important insights into redistricting can be gained by formulating and analyzing the problem with a Markov Chain Monte Carlo framework that utilizes optimization heuristics to inform transition proposals.
Speaker(s):

Wearable Brain-Machine Interface Architectures for Neurocognitive Stress

Mon, Feb 10, 2020, 4:30 pm
The human body responds to neurocognitive stress in multiple ways through its autonomic nervous system. Changes in skin conductance measurements indicate sudomotor nerve activity, and could be used in inferring the underlying autonomic nervous system stimulation. We model skin conductance measurements using a state-space model with sparse...
Speaker(s):

Scalable Semidefinite Programming

Mon, Feb 10, 2020, 4:00 pm
Semidefinite programming (SDP) is a powerful framework from convex optimization that has striking potential for data science applications. This talk develops new provably correct algorithms for solving large SDP problems by economizing on both the storage and the arithmetic costs. We present two methods: one based on sketching, and the other on...
Speaker(s):

Targeted Machine Learning for Causal Inference

Fri, Feb 7, 2020, 12:00 pm
We review targeted minimum loss estimation (TMLE), which provides a general template for the construction of asymptotically efficient plug-in estimators of a target estimand for infinite dimensional models.
Speaker(s):

Pages