Upcoming Seminars

Speaker

Dr. Isaac Sheidlower, Postdoctoral Researcher at Brown University, Rhode Island, hosted by Dr. Matthew Taylor

Title

Robots as Social Goods: Empowering Users to Direct Interactions

Abstract
Much fundamental research in robotics and human-robot interaction (HRI) assume an individual ownership model of robots. In other words, families or individuals buy a robot to be used indefinitely, in their home for example. In this talk, we will propose an alternative: robots as social goods. Robots that are social goods, such as robots that can be borrowed from the public library, must work for a wide range of people on many different tasks with limited amounts of time. I will talk about how these social goods models of robots necessitate changes in how we consider creating these systems, using reinforcement learning and robot learning as the technical frame. Specifically, I discuss “empowerment strategies” which compensate for the inability of designers and researchers to account for every type of user and situation. The talk will conclude discussing the further development of empowerment strategies for different types of users and situations that these social goods robots will face.

Presenter Bio
Isaac Sheidlower is a postdoctoral researcher at Brown University in the Department of Computer Science. After completing a Bachelors at Rutgers University New Brunswick, he pursued his PhD at Tufts University in Computer Science under Dr. Elaine Short. During his PhD he published works at conferences like HRI and IROS on algorithmic human robot interaction. He now works with Assistant Professor Serena Booth in the Giraffe Lab at Brown, where his research focuses on creating robots as social goods, both by empowering end-users to have control over robots and algorithms, and by critically analyzing different models of robot ownership from a socio-technical perspective. 

Website

Isaac Sheidlower

Timing & Location

UComm Seminar Room 2-108, pizza from 11:30, seminar from noon to 1

Add event to calendar

Add event

Speaker

Dr. Abby Azari, Assistant Professor, University of Alberta (Physics, Electrical and Computer Engineering), research Fellow and Canada CIFAR AI Chair, Alberta Machine Intelligence Institute

Title

Uncertainty Aware Machine Learning for Preparing for Space and Planetary Exploration 

Abstract
The earliest interplanetary missions launched in the 1970s returned a few hundred gigabytes of data to Earth. In contrast, planetary missions today are collecting multiple terabytes of data. These missions are transforming the field of planetary space physics rapidly into an observationally rich field. At the same time, future exploration missions require autonomy to fulfill their science goals. These data volumes, and natural autonomy requirements, have prompted the use of data science methods, including machine learning, for planetary science and exploration.

Machine learning methods are particularly useful in providing system-wide perspectives which further our understanding of current, and past, planetary space environments. A planetary space environment is the region stretching from the upper ionized atmosphere (ionosphere) to the bow shock which forms upstream from the planet in the solar wind. Understanding how mass, momentum, and energy flow through large volume of space helps us understand atmospheric dynamics ¬and loss, auroral causation, and in general, build a cohesive understanding of our solar system. 

However, to build this understanding, we must send missions to planets where we have limited, prior observations. Instead, in preparing for these missions we utilize physics-based, often computationally expensive, models. This is a challenge for the planning of future, autonomy required, planetary exploration missions. Machine learning sits poised as a possible solution to assist in mission planning, if integrated with uncertainties and physics-based models.

In this talk I will discuss the challenge of reasoning about future planetary exploration with limited observations; and discuss machine learning as a possible solution. I will then present ongoing work in preparing for possible large-scale missions to regions of the solar system with limited observations (e.g. within the Sun’s corona, in Uranus’ space environment, to sample Europa’s interaction with the Jovian magnetosphere).

Presenter Bio
Dr. Azari is an Assistant Professor jointly appointed in the departments of Physics and Electrical and Computer Engineering at the University of Alberta. She is also a Canada CIFAR AI Chair and research Fellow at the Alberta Machine Intelligence Institute.

Her research group aims to develop the use of machine intelligence for scientific discovery in space science and exploration. They focus on addressing outstanding challenges in uncertainty quantification and the inclusion of physical information. These challenges are broadly shared between scientific domains and the group’s focus centers on probabilistic machine learning and inverse problems.

Dr. Azari is also a Science Team Member of the NASA MAVEN mission to Mars where she leads machine learning research as relevant to studying Mars’ space environment. Previously, she was an UBC Data Science Fellow, and a post-doctoral researcher at UC Berkeley’s Space Science Lab. Her PhD is from the University of Michigan College of Engineering’s Climate and Space department where she was an NSF Graduate Research Fellow and NASA Earth and Space Sciences Fellow. Dr Azari spent several years in space and climate policy at IDA’s Science and Technology Institute before pursuing graduate education.

Website
Abby Azari

Timing & Location

Pizza in UComm Seminar Room 2-108 from 11:30 to noon

Seminar in UComm Gregory Able Community Hall Room 2-450 from noon to 1

Add event to calendar

Add event

Speaker

Vlad Tkachuk, PhD student at the UofA, supervised by Dr. Csaba Szepesvari & Dr. Xiaoqi Tan

Title

TBA

Abstract
TBA

Presenter Bio
TBA

Timing & Location

UComm Seminar Room 2-108, pizza from 11:30, seminar from noon to 1

Add event to calendar

TBA

NO SEMINAR - Reading Week

Speaker

Esraa Elelimy, PhD student at the University of Alberta, supervised by Dr. Martha White

Title

TBA

Abstract
TBA

Presenter Bio
TBA

Timing & Location

UComm Seminar Room 2-108, pizza from 11:30, seminar from noon to 1

Add event to calendar

TBA

Speaker

Dr. Dieter Büchler, Amii Fellow & Assistant Professor in the Department of Computing Science at the University of Alberta

Title

TBA

Abstract
TBA

Presenter Bio
TBA

Timing & Location

Pizza in UComm Seminar Room 2-108 from 11:30 to noon

Seminar in UComm Alfred Sorenson Community Hall Room 2-350 from noon to 1

Add event to calendar

TBA

Speaker

TBA

Speaker

Dr. Zhou Yang, Amii Fellow & Assistant Professor in the Department of Computing Science at the University of Alberta

Title

TBA

Abstract
TBA

Presenter Bio
TBA

Timing & Location

Pizza in UComm Seminar Room 2-108 from 11:30 to noon

Seminar in UComm Alfred Sorenson Community Hall Room 2-350 from noon to 1

Add event to calendar

TBA

NO SEMINARS - Winter Closure

Speaker

Dr. Tony Yousefnezhad, Senior Data Scientist at National Bank of Canada, hosted by Dr. Russ Greiner

Title

Orthogonal Contrastive Learning for Multi-Representation fMRI Analysis

Abstract
Functional MRI offers a powerful window into human cognition, yet challenges such as low signal-to-noise ratio, high dimensionality, and limited sample sizes remain major barriers—especially when integrating data across subjects or imaging sites. In this talk, we will introduce Orthogonal Contrastive Learning (OCL), a unified framework for aligning and analyzing multi-subject fMRI data without requiring temporal synchronization or equal time-series lengths.

OCL leverages two identical encoder networks: an online network trained with a contrastive objective that brings same-stimulus responses closer while separating different ones, and a target network that tracks the online model through an exponential moving average for stable learning. Each layer integrates QR decomposition for orthogonal feature extraction, locality-sensitive hashing (LSH) for compact subject-specific signatures, positional encoding for temporal-spatial fusion, and a transformer encoder for generating discriminative neural embeddings. I will also discuss OCL’s unsupervised pretraining on synthetic fMRI-like data and its transfer learning workflow for multi-site applications.

Presenter Bio
Dr. Tony Yousefnezhad is a Senior Data Scientist in the Department of Information Management at the National Bank of Canada, with cross-continental experience spanning Eurasia, East Asia, and North America. In addition to his industry role, he actively contributes to academic research and open-source innovation through his self-founded company, Learning By Machine. His research is at the forefront of pioneering advancements in machine learning, with a focus on deep learning, natural language processing (NLP), and reinforcement learning (RL) methodologies. These developments are designed to analyze a wide range of data modalities, including time series, text, images, audio, and wearable signals.

Website

Tony Muhammad Yousefnezhad

Timing & Location

UComm Seminar Room 2-108, pizza from 11:30, seminar from noon to 1

Add event to calendar

Add to calendar

Speaker

TBA

Speaker

TBA

Speaker

Dr. Carrie Demmans Epp, Amii Fellow & Associate Professor in the Department of Computing Science at the University of Alberta

Title

TBA

Abstract
TBA

Presenter Bio
TBA

Timing & Location

Pizza in UComm Seminar Room 2-108 from 11:30 to noon

Seminar in UComm Alfred Sorenson Community Hall Room 2-350 from noon to 1

Add event to calendar

TBA