Past events

CS&E Colloquium: Fundamental Problems in AI: Transferability, Compressibility and Generalization

Thursday, Feb. 29, 2024, 11:15 a.m. through Thursday, Feb. 29, 2024, 12:15 p.m.

Keller Hall 3-180

The computer science colloquium takes place on Mondays and Fridays from 11:15 a.m. - 12:15 p.m. This week's speaker, Tomer Galanti (MIT), will be giving a talk titled "Fundamental Problems in AI: Transferability, Compressibility and Generalization".

Abstract

In this talk, we delve into several fundamental questions in deep learning. We start by addressing the question, "What are good representations of data?" Recent studies have shown that the representations learned by a single classifier over multiple classes can be easily adapted to new classes with very few samples. We offer a compelling explanation for this behavior by drawing a relationship between transferability and an emergent property known as neural collapse. Later, we explore why certain architectures, such as convolutional networks, outperform fully-connected networks, providing theoretical support for how their inherent sparsity aids learning with fewer samples. Lastly, I present recent findings on how training hyperparameters implicitly control the ranks of weight matrices, consequently affecting the model's compressibility and the dimensionality of the learned features.

Additionally, I will describe how this research integrates into a broader research program where I aim to develop realistic models of contemporary learning settings to guide practices in deep learning and artificial intelligence. Utilizing both theory and experiments, I study fundamental questions in the field of deep learning, including why certain architectural choices improve performance or convergence rates, when transfer learning and self-supervised learning work, and what kinds of data representations are learned in practical settings.

Biography

Tomer Galanti is a Postdoctoral Associate at the Center for Brains, Minds, and Machines at MIT, where he focuses on the theoretical and algorithmic aspects of deep learning. He received his Ph.D. in Computer Science from Tel Aviv University, during which he served as a Research Scientist Intern at Google DeepMind's Foundations team. He has published numerous papers in top-tier conferences and journals, including NeurIPS, ICML, ICLR, and JMLR. Notably, his paper "On the Modularity of Hypernetworks" was awarded an oral presentation at NeurIPS 2020.

MSSE Information Session (In Person)

Wednesday, Feb. 28, 2024, 1 p.m. through Wednesday, Feb. 28, 2024, 2 p.m.

When: February 28th, 2024
Time: 1-2 p.m. CST 
Where: Keller Hall 3-180/3-176
Parking Information: Kenneth H. Keller Hal - Parking

RSVP to attend!

Learn about the MSSE program at the upcoming in-person information session on February 28 from 1-2 p.m. CST.

Info sessions are recommended for those who have at least 1-2 years of software engineering experience.

During each session, MSSE staff will review:

  • Requirements (general)
  • Applying
  • Prerequisite requirements
  • What makes a strong applicant
  • Funding
  • Resources
  • Common questions
  • Questions from attendees
     

RSVP to attend!

AI for Mental Health Webinar with Stevie Chancellor

Wednesday, Feb. 28, 2024, Noon through Wednesday, Feb. 28, 2024, 1 p.m.

Online.

Artificial Intelligence is now at the forefront of technological interest in solving socially challenging problems, like identifying people who may discuss dangerous mental illness behaviors online (e.g. suicidal ideation, self-injury, and opioid addiction). We urgently need better AI to handle the volume and risk of this content in social networks. However, it is important to create AI and interventions in this space that are ethical and helpful, or we risk harming the very people we intend to help. Assistant Professor Stevie Chancellor will discuss the promises and perils for AI that predicts and intervenes in mental health in social media, and what we can do to make it more technically rigorous, ethical, and compassionate toward people in distress. She will discuss recent work in her research group on TikTok and mental health, and visions for the future of AI to assist in socially hard problems.

 
 

Computer Science & Data Science Graduate Student Department Head Town Hall

Monday, Feb. 26, 2024, 3 p.m. through Monday, Feb. 26, 2024, 4 p.m.

3-180 Keller Hall

RSVP

Please join us at the Computer Science and Data Science Graduate Student Department Head Town Hall. Light refreshments and snacks will be available.

DATE: Monday, February 26th 3 - 4 p.m.
LOCATION: 3-180 (in-person only event; no Zoom stream)
 

This is your chance to voice your opinion and offer critical feedback on teaching, student services, and any other items you think can be improved.  Your feedback and insights are important to help us improve your graduate experience.

Please use the link below to RSVP, or provide feedback regarding your experiences in your computer science courses and within the department. Please note that you can remain anonymous to provide feedback:

RSVP Link

Computer Science & Data Science Undergraduate Student Department Head Town Hall

Monday, Feb. 26, 2024, 1:30 p.m. through Monday, Feb. 26, 2024, 2:30 p.m.

3-180 Keller Hall

RSVP

Please join us at the Computer Science and Data Science Undergraduate Student Department Head Town Hall. Light refreshments and snacks will be available.

DATE: Monday, February 26th 1:30 pm - 2:30
LOCATION: Keller 3-180 (in-person only event; no Zoom stream)
 

This is your chance to voice your opinion and offer critical feedback on teaching, student services, and any other items you think can be improved.  Your feedback and insights are important to help us improve your graduate experience.

Please use the link below to RSVP, or provide feedback regarding your experiences in your computer science courses and within the department. Please note that you can remain anonymous to provide feedback:

RSVP Link

CS&E Colloquium: How Do We Get There?: Toward Intelligent Behavior Intervention

Friday, Feb. 23, 2024, 11:15 a.m. through Friday, Feb. 23, 2024, 12:15 p.m.

Keller Hall 3-180

The computer science colloquium takes place on Fridays from 11:15 a.m. - 12:15 p.m. This week's speaker, Xuhai "Orson" Xu (MIT), will be giving a talk titled "How Do We Get There?: Toward Intelligent Behavior Intervention."

Abstract

As the intelligence of everyday smart devices continues to evolve, they can already monitor basic health behaviors such as physical activities and heart rates. The vision of an intelligent behavior change intervention pipeline for health -- combining behavior modeling & interaction design -- seems to be within reach. How do we get there?

In this talk, I will introduce a comprehensive intervention pipeline that bridges behavior science theory-driven designs and generalizable behavior models. I will also introduce my efforts on passive sensing datasets, human-centered algorithms, and a benchmark platform that drives the community toward more robust and deployable intervention systems for health and well-being.

Biography

Xuhai "Orson" Xu is a postdoc at MIT EECS. He received his PhD at the University of Washington. Xu develops intelligent behavior intervention systems to promote human health and well-being. Xu's research covers two aspects -- 1) building deployable human-centered behavior models and 2) designing interactive user experiences -- to establish a complete system to improve end-users' well-being. Moreover, his research also goes beyond end-users and supports health experts by designing new human-AI collaboration paradigms in clinical settings. Xu's research straddles multiple disciplines, including human-computer interaction, applied machine learning, and health. Xu has earned several awards, including 9 Best Paper, Best Paper Honorable Mention, and Best Artifact awards. His research has been covered by media outlets such as The Washington Post, Communication of ACM, and ACM News. He was recognized as the Gaetano Borriello Outstanding Student Award Winner at UbiComp 2022, the 2023 UW Distinguished Dissertation Award, and the 2024 Innovation and Technology Award at the Western Association of Graduate Schools.

BICB Colloquium: Shijia Zhu

Thursday, Feb. 22, 2024, 5 p.m. through Thursday, Feb. 22, 2024, 6 p.m.

MCB 2-122 on the Twin Cities campus

Usq 419 on the Rochester campus

Virtually

BICB Colloquium Faculty Nomination Talks: Join us in person on the UMR campus in room 419, on the Twin Cities campus in MCB 2-122 or virtually at 5 p.m.
 

Dr. Shijia Zhu is presenting as part of the nomination process for new BICB faculty. He is an Assistant Professor in the Department of Laboratory Medicine and Pathology at the Medical School.


Title

Novel Computational Methods of Multi-omics Data Analysis in Disease Studies

Abstract

Dr. Zhu integrates diverse multi-omics data in his studies, including the spatial transcriptomics, Pacbio SMRT-seq long read, and traditional bulk sequencing technologies. Meanwhile, he designed the novel computational methods of multi-omics data analysis tailored for disease studies. In this presentation, he will talk about how to align the spot-level spatial transcriptomics to the nuclear morphology to achieve the single-cell level spatial data analysis, therefore enabling the real cell-cell interaction in disease tissues rather than the current spot-spot interaction. In addition, he will talk about how to combine the long read and short read sequencing to accurately characterize the pathogenic alternative splicing isoforms, which further contribute to the novel therapeutic strategy. Last, he will talk about how to screen the disease driving factors from a very small sample size via aggregating the downstream targets to minimize the false positives and improve the discovery power.

Biography

In 2012, Dr. Zhu obtained his Ph.D. degree in Computer Science and Bioinformatics from Harbin Institute of Technology, in China. He designed the novel methods of regulatory network among epigenetic marker, gene expression and alternative splicing. In 2013-2017, he did his postdoc at Icahn School of Medicine at Mount Sinai, at New York. During this period, he was working on the Pacbio SMRT-seq to study both novel form of DNA methylation in the eukaryotes genome and the alternative splicing isoforms. Since 2018, he is a research-track Assistant Professor at University of Texas Southwestern Medical Center. He is utilizing multi-omics data to study the digestive liver disease and liver cancer.

Computer Science Learning Abroad Online Info Session

Tuesday, Feb. 20, 2024, 2 p.m. through Tuesday, Feb. 20, 2024, 3 p.m.

Online. Register to get login details.

This virtual info session is for Computer Science students who are interested in studying abroad to learn more about program opportunities. We will highlight programs featured on the Computer Science Major Advising Page for Learning Abroad and help both CLA and CSE Computer Science students to learn more about the process. Programs in many regions of the world will be featured to help Computer Science students better understand how to gain a global perspective and take advantage of learning abroad opportunities.

 
 

CS&E Colloquium: Socially-Informed Human-Centered AI

Monday, Feb. 19, 2024, 11:15 a.m. through Monday, Feb. 19, 2024, 12:15 p.m.

Keller Hall 3-180

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m. This week's speaker, Chan Young Park (Carnegie Mellon University), will be giving a talk titled "Socially-Informed Human-Centered AI."

Abstract

The recent advancements in generative AI, largely driven by training larger models with more data, unlock exciting new opportunities. However, these scaling-centric approaches overlook the human aspect of language, where meaning goes beyond just words and involves people and social context. This limitation leads to models that generate generic responses, potentially biased towards dominant social groups. In this talk, I present my research on developing socially-informed, human-centered AI. I demonstrate how incorporating social context, such as community and speaker information, can improve AI models’  adaptability, effectiveness, and fairness across all stages of development, from data to model and evaluation. I conclude by outlining my research vision for building AI models that foster a safer, inclusive, and personalized human experience.

Biography

Chan Young Park is a final-year PhD candidate in the School of Computer Science at Carnegie Mellon University, advised by Professor Yulia Tsvetkov. She is currently a visiting PhD student at the University of Washington. Her research focuses on the intersection of natural language processing, computational social science, and AI ethics. Her work has been published in top conferences and journals, including PNAS, ACL, EMNLP, WWW, and ICWSM, and was featured in MIT Tech Review and the Washington Post. She received the ACL Best Paper Award and Wikimedia Foundation Research Award of the Year 2023, and was selected as a University of Chicago Rising Stars in Data Science. Chan Young is also a recipient of the K&L Gates Presidential Fellowship and Korea Foundation for Advanced Studies PhD fellowship. 

Graduate Programs Online Information Session

Monday, Feb. 12, 2024, 2:30 p.m. through Monday, Feb. 12, 2024, 3:30 p.m.

Virtual meeting - RSVP online 

RSVP today!.

During each session, the graduate staff will review:

  • Requirements (general)
  • Applying
  • Prerequisite requirements
  • What makes a strong applicant
  • Funding
  • Resources
  • Common questions
  • Questions from attendees

Students considering the following programs should attend:

More About Department News and Events

More About Events