Past Events

Michael Perlmutter (University of California, Los Angeles)

The scattering transform is a wavelet-based feed-forward network originally introduced by S. Mallat to improve our theoretical understanding of convolutional neural networks (CNNs). Like the front end of a CNN, it produces a latent representation of input signal through an alternating sequence of convolutions and non-linearities. Following Mallat's original paper, subsequent work has shown that this latent representation can be used to synthesize new input signals such as textures. In a somewhat orthogonal extension, there has also been a number of papers which have shown how to adapt the scattering transform to graph-structured data.

In my talk, I will present a new network which combines these two ideas and uses the graph scattering transform to generate new molecules with the intended application being drug discovery. In order to ensure that the molecules produced by our network satisfy the laws of chemistry and resemble actual drugs, we use a regularized autoencoder to learn a compressed representation of the scattering coefficients of each graph and a generative adversarial network (GAN) to produce new molecules directly from this compressed representation.

Michael Perlmutter is a Hedrick Assistant Adjunct Professor in the department of mathematics at the University of California, Los Angeles. Previously he has held postdoctoral positions in the department of Statistics and Operations Research at the University of North Carolina at Chapel Hill and in the department of Computational Math., Science and Engineering at Michigan State University. He earned his PHD in Mathematics from Purdue University.

Fatemeh Sheikholeslami (Bosch Center for Artificial Intelligence)

Researchers have repeatedly shown that it is possible to craft adversarial attacks, i.e., small perturbations that significantly change the class label, on deep classifiers and considerably degrade their performance. This fragility can significantly hinder the deployment of deep learning-based methods in safety-critical applications. To address this, adversarial attacks can be defended against either by building robust classifiers or, by creating classifiers that can detect the presence of adversarial perturbations. I will talk about a couple of algorithms that we have developed at BCAI which provide certified defenses against different threat models.

Fatemeh Sheikholeslami received her PhD in Electrical Engineering from University of Minnesota in 2019, under the supervision of Professor Georgios Giannakis. She is currently a Machine Learning Research Scientist at Bosch Center for Artificial Intelligence with the Safe and Robust Deep Learning group.

Eric Wespi (Boston Scientific)

Implementing AI models in a manufacturing environment can present several challenges.  In this session we will discuss both technical and cultural considerations for the deployment of AI-based machine vision in a regulated industry.  Topics include supporting data architecture, messaging to senior leadership, addressing uncertainty about black-box models, make/buy decisions, and talent acquisition and retention.

Eric Wespi is a Data Science Fellow at Boston Scientific.  He manages a Data Science team within the Process Development organization and leads efforts to implement AI-based computer vision in manufacturing facilities globally.  Eric has worked at Boston Scientific for 6 years, prior to which he held various engineering roles at Intel.  He has a bachelor’s degree in Chemical Engineering from the University of Minnesota and an MBA from Arizona State University.  In his spare time Eric enjoys spending time with his family, cooking, and various other outdoor activities.

Yariv Aizenbud (Yale University)

A common task in many data-driven applications is to find a low dimensional manifold that describes the data accurately. Estimating a manifold from noisy samples has proven to be a challenging task. Indeed, even after decades of research, there is no (computationally tractable) algorithm that accurately estimates a manifold from noisy samples with a constant level of noise.

In this talk, we will present a method that estimates a manifold and its tangent in the ambient space. Moreover, we establish rigorous convergence rates, which are essentially as good as existing convergence rates for function estimation.

This is a joint work with Barak Sober.

Yariv Aizenbud is a Gibbs assistant professor of applied mathematics at Yale University. Previously, he completed his Ph.D. at Tel-Aviv University. His research is focused on statistical recovery of geometric structures. from data. The applications for his research include computational biology, manifold learning, and numerical linear algebra.

Jeffrey Moulton (Instacart)

Jeff will talk about what it's like to work as a data scientist in tech and go over a couple examples of the types of problems that arise in digital advertising.

Advisory: Register here to attend the Field of Dreams!

Poster

Organizers

• David Goldberg — Purdue University
• Daniel Spirn — University of Minnesota, Twin Cities

The Field of Dreams Conference introduces potential graduate students to graduate programs in the mathematical sciences at Alliance schools as well as professional opportunities in these fields. Scholars spend time with faculty mentors from the Alliance schools, get advice on graduate school applications, and attend seminars on graduate school preparation and expectations as well as career seminars.

Tentative List of Speakers

• Ricardo Cortez (Tulane University) (confirmed)
• Carrie Eaton (Bates College) (confirmed)
• Leslie McClure (Drexel University) (confirmed)
• Shannan Paul (NUTS, ltd) (confirmed)

Organizers

• Christine Berkesch — University of Minnesota, Twin Cities
• Daniel Erman — University of Wisconsin, Madison
• Jason McCullough — Iowa State University

This mini-conference is hosted jointly by Iowa State, Minnesota, and Wisconsin and highlights work in commutative algebra and related fields like algebraic geometry, number theory, combinatorics, and more. We have colloquium-style talks targeted at a broad audience of people interested in algebra.

Jiguang Shen (Microsoft Research)

Intelligent search, powered by natural language processing (NLP) algorithms, helps individuals and enterprise customers find useful information they need at an unprecedented scale.  Compared to the traditional web search engines,  there are a lot of new challenges in this rising popular domain.  In this talk,  I will talk about my experience working at the public web search engine Microsoft Bing and the latest work we have done at Microsoft Research & Incubation on building intelligent search systems over enterprise documents. 

Jiguang Shen received his Ph.D. in Applied Mathematics from University of Minnesota in 2017, under the supervision of Professor Bernardo Cockburn.  He is currently a Senior Applied Science Manager at Microsoft working on building search and ranking systems.

Jimmy Broomfield (Target Corporation)

Have you ever wondered how supply chains make decisions about purchasing and transport? Or perhaps you've stayed up at night wondering how energy companies plan for customer demand. Time series forecasting is a major component used to help business teams solve these problems. In this talk, I'll share my career journey in the world of industrial forecasting. We'll touch on the topics of data preparation, time series models, accuracy metrics, high level architecture, and compute/time constraints.

Jimmy graduated from the University of Minnesota in 2019 with a PhD in Math and joined Ecolab's advanced analytics team where he primarily worked in the field of time series analysis and forecasting.  During his time at Ecolab, Jimmy made contributions to the enterprise's time series classification framework by introducing novel wavelet and frequency based features.  He also served as a team lead with the responsibility for architecting, building, and validating a modern supply chain forecasting system for Ecolab's industrial chemical distribution.  Jimmy recently made a career transition to the demand forecasting team at Target where he hopes to continue his journey toward understanding industrial forecasting challenges and solutions.

Ryan Murray (North Carolina State University)

• Slides

Widespread application of modern machine learning has increased the need for robust statistical algorithms. One fundamental geometric quantity in robust statistics is known as a data depth, which generalizes the notion of quantiles and medians to multiple dimensions. This talk will discuss recent work (in collaboration with Martin Molina-Fructuoso) which connects certain types of data depths with Hamilton-Jacobi equations, a first-order partial differential equation that is fundamental to control theory. Computational considerations, connections to convex geometry and a number of related open problems will all be discussed.

Ryan Murray received his PhD in mathematics from Carnegie Mellon University in 2016, and was a Chowla Assistant Professor at Penn State University from 2016-2019. Since 2019 he is an assistant professor at North Carolina State University, department of mathematics.