Embedded Files
NEW LOCATIONS - Find us in UComm 2-108 (regular weekly seminars) or UComm 2-350 (monthly Fellows seminars)
December 20 & 27 & January 3
NO SEMINARS - Winter Closure
December 13
Unifying supervised learning and reinforcement learning via an MRP formulation: generalized TD learning
Dr. Yangchen Pan, Department of Engineering Science, University of Oxford
Hosted by Dr. Martha White
Abstract:
This presentation challenges the traditional i.i.d. assumption in statistical learning by modeling data as interconnected through a Markov reward process (MRP). We reformulate supervised learning as an on-policy policy evaluation in reinforcement learning (RL) and propose a generalized temporal difference (TD) learning algorithm. Our theoretical analysis connects linear TD solutions to ordinary least squares (OLS), showing TD’s advantage when noise is correlated. We prove convergence under linear function approximation. Empirical studies validate our approach, showcasing its utility in tasks like regression and deep learning-based image classification.
Presenter Bio:
Dr. Yangchen Pan is a Lecturer in Machine Learning at the Department of Engineering Science, University of Oxford. He previously earned his Ph.D. from the University of Alberta under the supervision of Prof. Martha White and Prof. Amir-massoud Farahmand. His research focuses on achieving sample-efficient generalization with scalable computation, with particular interest in learning settings involving distribution shifts, including robust learning, reinforcement learning, and continual learning.
December 6
PulseMedica: Applying ML Technologies to Screen and Treat Eye Floaters
Dr. Chris Ceroici, PulseMedica
Co-hosted by Technology Alberta
Abstract:
PulseMedica is an Edmonton-based startup developing a platform that is intended to be the first safe, effective, and non-invasive system to screen and treat vitreoretinal disease, starting with symptomatic vitreous opacities (eye floaters). This seminar will focus on how PulseMedica is applying machine learning to detect, track and treat eye floaters.
Presenter Bio:
Dr. Chris Ceroici received his MSc in Electrical Engineering from the University of Waterloo and his PhD in Biomedical Engineering from the University of Alberta, focusing mainly on medical image processing and reconstruction. For the last 4 years he has been the machine learning team lead at PulseMedica, finding and applying machine learning solutions to help diagnose and treat vitreoretinal disease.
November 29
Essential Offline RL Theories for Algorithm Developers
Fengdi Che, PhD student, University of Alberta
Supervised by Dr. Rupam Mahmood
Abstract:
The talk will offer intuitive explanations of the necessary and sufficient conditions for theoretical guarantees, enabling researchers to identify the hardness of offline RL and discuss the potential techniques to solve offline RL tasks.
Presenter Bio:
Fengdi Che is a fourth-year PhD student at the University of Alberta, supervised by Dr. A. Rupam Mahmood. Her primary research interest focuses on effectively using data, especially for reinforcement learning. She designs and analyzes algorithms that leverage datasets experiencing distribution shifts and investigates how data should be collected.
November 22
Leveraging Reinforcement Learning for Player Interaction Gameplay Mechanics Generation
Johor Jara Gonzalez, PhD student, University of Alberta
Supervised by Dr. Matthew Guzdial
Abstract:
Making game mechanics is challenging due to the need for intricate design and programming. Procedural Content Generation (PCG) is a prevalent aspect of modern video game development, enabling the creation of dynamic and engaging content. Ensuring these mechanics achieve the desired balance and player experience adds an extra layer of complexity and requires testing, player feedback, and iterative adjustments. Although algorithms like A* can evaluate whether a player can reach an area or defeat an enemy, they do not capture the way a player learns or interacts with new mechanics. Reinforcement Learning (RL), with its ability to learn, presents a promising approach to overcome these limitations.
Presenter Bio:
Ph.D. student at the University of Alberta, part of the GRAIL lab, interested in computer creativity and Reinforcement Learning, and Game developer in the free times!
November 15
NO SEMINAR - Reading Week
November 8
From Data to Predictions: Using Physics and Domain Expertise to Maximize AI’s Potential
Afzal Memon, Founder & CEO, Fluidsdata
Co-hosted by Technology Alberta
Abstract:
As AI evolves rapidly, various industries are leveraging AI-ML algorithms to maximize data use and reduce operational costs. However, limited high-quality data poses challenges, often resulting in suboptimal ROI. This seminar will explore strategies for overcoming these challenges by integrating well-established principles from physics and domain expertise into AI models, thus enhancing prediction accuracy for fluids characterization in the energy industry. By applying these methods, we can bridge data gaps and unlock AI's true potential for robust, actionable insights and predictions.
Presenter Bio:
Afzal Memon is the founder and CEO of fluidsdata, an innovative AI-ML company with domain expertise that is revolutionizing the fluids characterization space with its cutting-edge solutions in Energy Industry. With a keen focus on innovation, he is actively involved in the new technology development and AI software applications, constantly pushing the boundaries of what's possible in the field of fluids characterizations. Afzal is a subject matter expert (SME) in the area of fluid characterizations in oil and gas industry. He brings over two decades of industry experience and he has co-authored 35+ technical publications.
November 1
SEMINAR CANCELLED
October 25
True Novelty and Out of Distribution Generation through Procedural Content Generation via Knowledge Transfer
Dr. Matthew Guzdial, Assistant Professor, University of Alberta
Abstract:
Generative AI (GenAI) tools have had a major impact on the general public, but they are not the first instance of generating content with AI. Procedural Content Generation (PCG) as a field focused on content generation dates back to 1978. However, what both PCG and GenAI have in common is a difficulty with generating out of distribution (OOD) content, totally new things that have never been seen before. In this talk, we’ll discuss the recent “Procedural Content Generation via Knowledge Transfer” framework and how this can be used to generate OOD content for video games, music, and more.
Presenter Bio:
Dr. Matthew Guzdial is an Assistant Professor in the Computing Science department of the University of Alberta and a Canada CIFAR AI Chair at the Alberta Machine Intelligence Institute (Amii). His research focuses on the intersection of machine learning, creativity, and human-centered computing. He is a recipient of an Early Career Researcher Award from NSERC, an Early Career invited talk from IJCAI, a Unity Graduate Fellowship, and two best conference paper awards from the International Conference on Computational Creativity. His work has been featured in the BBC, WIRED, Popular Science, and Time.
October 18
SEMINAR CANCELLED
October 11
Synergy of Graph Data Management and Machine Learning in Explainability and Query Answering
Dr. Arijit Khan, Associate Professor, Aalborg University, Denmark
Hosted by Dr. Davood Rafiei
Abstract:
Graph data, e.g., social and biological networks, financial transactions, knowledge graphs, and transportation systems are pervasive in the natural world, where nodes are entities with features, and edges denote relations among them. Machine learning and recently, graph neural networks become ubiquitous, e.g., in cheminformatics, bioinformatics, fraud detection, question answering, and recommendation over knowledge graphs. In this talk, I shall introduce our ongoing works about the synergy of graph data management and graph machine learning in the context of graph neural network explainability and query answering. In the first direction, I shall discuss how data management techniques can assist in generating user‐friendly, configurable, queryable, and robust explanations for graph neural networks. In the second direction, I shall provide an overview of our user‐friendly, deep learning‐based, scalable techniques and systems for querying knowledge graphs.
Presenter Bio:
Dr. Arijit Khan is an Associate Professor at Aalborg University, Denmark. His PhD is from University of California, Santa Barbara, USA, and he did a post-doc in the Systems group at ETH Zurich, Switzerland. He has been an assistant professor in the School of Computer Science and Engineering, Nanyang Technological University, Singapore. His research is on data management and machine learning for the emerging problems in large graphs. He is an IEEE senior member and an ACM distinguished speaker. Arijit is the recipient of the IBM Ph.D. Fellowship (2012-13), a VLDB Distinguished Reviewer award (2022), and a SIGMOD Distinguished PC award (2024). He is the author of a book on uncertain graphs and over 80 publications in top venues including ACM SIGMOD, VLDB, IEEE TKDE, IEEE ICDE, SIAM SDM, USENIX ATC, EDBT, The Web Conference (WWW), ACM WSDM, ACM CIKM, ACM TKDD, and ACM SIGMOD Record. Dr Khan is serving as an associate editor of IEEE TKDE 2019-2024 and ACM TKDD 2023-now, proceedings chair of EDBT 2020, IEEE ICDE TKDE poster track co-chair 2023, ACM CIKM short paper track co-chair 2024, and IEEE ICDE demonstration paper track program co-chair 2024.
October 4
SEMINAR CANCELLED
September 27
Exploring Hybrid Planning: Insights and Practical Applications
Dr. Francesco Percassi
Hosted by Dr. Levi Lelis
Abstract:
This seminar explores PDDL+, a powerful planning formalism used to model hybrid systems in automated planning. It combines numeric and temporal elements, allowing for separate representation of an agent’s actions and exogenous environmental dynamics. While its expressive power makes PDDL+ tasks challenging, it also enables effective modelling of real-world problems. We will introduce the formalism from a theoretical perspective and highlight our key contributions. Finally, we will present a case study demonstrating its application in improving Urban Traffic Control.
Presenter Bio:
Dr. Francesco Percassi is a Research Fellow at the School of Computing and Engineering, University of Huddersfield. He earned his PhD in July 2019 from Università degli Studi di Brescia under the supervision of Professor Alfonso E. Gerevini. After completing his PhD, he joined the University of Huddersfield as a Research Fellow. His main research interests include automated planning, translations between planning formalisms, and the application of planning techniques to Urban Traffic Control.
September 20
Computational Semantics via Lexical Concepts
Ning Shi & Jai Riley, PhD students, University of Alberta
Supervised by Dr. Greg Kondrak
Abstract:
This presentation will cover four recent publications on computational semantics, which address the following research questions:
1. Can lexical gaps be detected using machine translation? (ACL 2024)
2. How can synonyms be generated for words in context? (*SEM 2024)
3. What is the link between semantic similarity and relatedness? (SemEval 2024)
4. Can a natural language inference model detect paraphrases? (*SEM 2024)
In our studies, we leverage large language models, and often obtain superior results, thus contributing to the development of a unified taxonomy of semantics.
Presenter Bio:
Ning Shi is a third-year PhD student working with Prof. Greg Kondrak. Before starting at the UofA, he worked as a senior algorithm engineer at Alibaba Group. Ning has graduate degrees from Georgia Tech, Syracuse University, and NYU. His doctoral research centers on establishing theoretical and computational connections between various semantic tasks in natural language processing (NLP), with the aim of enhancing their understanding and interpretability.
Jai Riley is a second-year MSc student working with Prof. Greg Kondrak. His research is also focused on semantic tasks in multilingual NLP.
September 13
Contrastive Decoding for Concepts in the Brain
Cory Efird, MSc student, University of Alberta
Supervised by Dr. Alona Fyshe
Abstract:
We present a novel data-driven method for identifying category-selective regions in the human brain that are consistent across multiple participants. By leveraging a massive fMRI dataset and a multi-modal (language and image) neural network (CLIP), we trained a highly accurate contrastive brain decoder to predict neural responses to naturalistic images in the human visual cortex. We then applied a novel adaptation of the DBSCAN clustering algorithm to identify clusters of voxels across multiple brains that decode similar concepts.
Presenter Bio:
Cory Efird is currently an MSc. student in the Computing Science Department at the University of Alberta, supervised by Dr. Alona Fyshe. His research blends deep learning and neuroscience to better understand brain function and visual perception.
September 6
Explaining and Improving Formula-Represented Heuristic Functions in Grid Pathfinding
Shuwei Wang, MSc student, University of Alberta
Supervised by Dr. Vadim Bulitko
Abstract:
We propose a visualization tool to explain synthesized heuristic formulae on video-game maps. We show examples of applying the tool to improve existing heuristic formulae. Furthermore, we show empirical results of synthesizing heuristic formulae with constrained subformula sizes and show that the constraints impose less effect on average for problems with varying goal locations than for problems with a shared goal location, and in general such constraints do not hurt heuristic’s guiding performance while improving their explainability.
Presenter Bio:
Shuwei Wang is a MSc. student in the Department of Computing Science at the University of Alberta, working with Prof. Vadim Bulitko. His research focuses on generating and explaining search heuristics. His general research interests include explainable AI, heuristic search and program synthesis.
August 30
Knowledge Distillation for Text Generation with Multi-Modality
Yuqiao Wen, PhD student, University of Alberta
Supervised by Dr. Lili Mou
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
Knowledge distillation (KD) is the process of transferring knowledge from a large teacher model to a small student model. A key challenge in KD is multi-modality, where given a text input (e.g., a prompt), there may be a large number of plausible ways to respond. In this talk, I will discuss ways to alleviate this problem in distribution-matching KD and multi-teacher KD, which also sheds light on future directions for addressing multi-modality in text generation.
Presenter Bio:
Yuqiao Wen is currently a second-year PhD student at the Department of Computing Science, University of Alberta, after having his MSc in 2022 and BSc in 2020. Yuqiao's research lies in developing efficient methods for large language models and making them more accessible for everyone; he has a focus on machine learning problems in knowledge distillation such as label bias and exposure bias. He has published a number of papers at top-tier venues such as ICLR and ACL.
August 23
Maintaining Plasticity Independent of Architecture Through Selective Reinitialization
J. Fernando Hernandez Garcia, PhD student, University of Alberta
Supervised by Dr. Rich Sutton
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
The problem of loss of plasticity in neural networks, in which a network loses its ability to learn from new observations when trained for an extended time, is a major limitation to implementing deep learning systems that learn continually. A tried and tested idea for maintaining plasticity is to sporadically reinitialize low-utility features in the network, an algorithm known as continual backpropagation. However, measuring the utility of features depends on the feature's connectivity pattern, which makes it difficult to combine continual backpropagation with any arbitrary network. This drawback is removed if one works at the lowest level in a network: the weights. In this talk, I present the successes and failures of continual backpropagation in maintaining plasticity in different architectures. Then, I present a new algorithm, selective weight reinitialization, which successfully maintains plasticity by reinitializing weights instead of features.
Presenter Bio:
J. Fernando Hernandez-Garcia is PhD student in the RLAI Lab at the University of Alberta, supervised by Dr. Richard Sutton. He aims to design intelligent systems that continually learn while interacting with the world.
Special Tuesday Seminar
August 20
Towards Autonomous Vehicles 2.0: Unifying Vision, Language, and Action within Embodied AI for Safe and Explainable Autonomous Driving
Shahin Atakishiyev, PhD student, University of Alberta
Supervised by Dr. Randy Goebel
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
More than three decades of autonomous driving research, primarily starting with ALVINN in 1988, have achieved significant milestones with traditional AI software. However, recent breakthroughs in Foundation Models via Large Language Models and Vision-Language Models motivate a next-generation autonomous vehicle (AV 2.0) and a gradual transition from a modular pipeline to end-to-end learning within Embodied AI. In this talk, I present challenges and opportunities with safety and explainability of AV 2.0 by drawing insights from critical analysis and empirical evidence.
Presenter Bio:
Shahin Atakishiyev is a PhD Candidate in the Department of Computing Science at the University of Alberta, working with Prof. Randy Goebel. His doctoral research focuses on the development of explainable AI approaches for autonomous vehicles. His general research interests include safe, ethical, human-centered, and explainable AI approaches applied to real-world problems.
August 16
Trajectory Data Suffices for Statistically Efficient Offline Reinforcement Learning with Linear Value Function Approximation and Good Data Coverage
Vlad Tkachuk, PhD student, University of Alberta
Supervised by Dr. Xiaoqi Tan & Dr. Csaba Szepesvári
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
We study offline reinforcement learning with linear value function approximation. Previous work showed that learning a nearly optimal policy is impossible without a large dataset size, even with a data coverage assumption. This work left open whether trajectory data could overcome this issue. We show that with trajectory data, a dataset of size polynomial in feature dimension, horizon, and data coverage coefficient suffices for learning a nearly optimal policy. The question of computational efficiency remains open.
Presenter Bio:
Vlad Tkachuk is a first-year PhD student in Computing Science at the University of Alberta, working under the supervision of Csaba Szepesvári and Xiaoqi Tan. He completed his master's degree at the University of Alberta, also under the supervision of Csaba Szepesvári. Before that, he obtained his bachelor's in Electrical Engineering from the University of Waterloo. His research interests lie primarily in reinforcement learning theory.
August 9
SEMINAR CANCELLED
August 2
AI Data-driven Corrosion Management Software
Dr. Tesfa Haile, CEO, Genesis Data Solutions
Co-hosted by Technology Alberta
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
The AI data-driven corrosion management software leverages advanced algorithms to predict, monitor, and mitigate corrosion in industrial systems. By integrating real-time data from sensors and historical records, the software provides accurate diagnostics and prognostics, enhancing maintenance strategies and reducing downtime. Its machine-learning capabilities continuously improve predictive accuracy, enabling proactive management of corrosion-related issues. This innovative solution optimizes asset integrity, extends equipment lifespan, and minimizes operational costs, ensuring safe and efficient industrial operations.
Presenter Bio:
Dr. Tesfa Haile, the founder of Genesis Data Solutions Inc., brings over 21 years of rich experience in government research centers, private consulting firms, and academia. He earned his Ph.D. in Engineering Science – Civil & Environmental Engineering from the University of Western Ontario. At Genesis Data Solutions, Dr. Haile provides both management and technical leadership to a diverse team, ensuring the company meets its objectives efficiently. His technical expertise encompasses the development of innovative industrial products, including AI tools, sensors, coatings, and environmentally conscious cement additives for the oil and gas industry, wastewater collection, and sanitary sewer operations. Dr. Haile's significant roles include chair and vice chair positions at the Association for Materials Protection and Performance (AMPP), formerly NACE International. He has led major government and industry-sponsored projects related to microbiologically influenced corrosion (MIC). Dr. Haile's professional journey includes an NSERC Postdoctoral Fellowship at Natural Resources Canada - CanmetMATERIALS, where he developed patented biosensors for monitoring bacterial activity causing corrosion in pipelines. He also made significant contributions as an MIC Expert at Broadsword Corrosion Engineering and served as a Senior Scientist at InnoTech Alberta. Dr. Haile's comprehensive background and leadership in various sectors underscore his commitment to advancing industrial innovation and operational excellence.
July 29
Special Monday Seminar
The EU AI Act: Persistent frailties
Dr. Kris Shrishak, Senior Fellow at the Irish Council for Civil Liberties
Hosted by Dr. Bailey Kacsmar, Department of Computing Science, University of Alberta
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
The EU AI Act has been finalized in early 2024. But whether it is worth its paper or not will depend on how it will be enforced in the next few years. This talk will take you on a journey of band-aid solutions in the AI Act since its first draft in 2021, and the frailties that persist: from its reliance on companies to act in good faith to the enforcement challenges. As researchers, these challenges offer us research problems whose solutions could contribute to stronger enforcement.
Presenter Bio:
Dr Kris Shrishak is a public interest technologist and an Enforce Senior Fellow at the Irish Council for Civil Liberties. He advises legislators on global AI governance (including EU AI Act). His work focusses on privacy tech, anti-surveillance, emerging technologies, and algorithmic decision making.
July 26
Source Code Obfuscation with Evolutionary Algorithms
José Miguel Aragón Jurado, PhD Candidate, Computer Engineering Department, University of Cádiz
Hosted by Dr. Abram Hindle, Department of Computing Science, University of Alberta
NOTE: LOCATION CHANGE - CSC B-10
Abstract:
Computing devices are ubiquitous and, with the rise of the Internet of Things, their presence is increasing. Software needs protection against attacks to prevent plagiarism and security breaches. Obfuscation, which makes code unintelligible, is a common protection technique. In this talk, we will define multiple combinatorial optimization problems and employ evolutionary algorithms to solve them. The results show significant improvements in obfuscation, outperforming the original programs and existing methods by a wide margin.
Presenter Bio:
José M. Aragón-Jurado is a PhD Candidate in the Computer Engineering department at the University of Cádiz. Currently, He is collaborating with Dr. Abram Hindle at the University of Alberta on his thesis titled "Software Optimization for a Green Internet of Things." His general research involves the use of machine learning algorithms and metaheuristic techniques to solve real-world problems. He has multiple research publications in high-impact journals and international conferences in the fields of software optimization, sustainability, cybersecurity, IoT, and video games.
July 19
NO SEMINAR
July 12
Learning Continually by Spectral Regularization
Alex Lewandowski, PhD student, University of Alberta
Abstract:
Neural networks can become less trainable over the course of learning, a phenomenon referred to as loss of plasticity. This talk will describe a spectral perspective on neural network trainability. At initialization, the distribution of singular values for the neural network parameters is relatively uniform. Over the course of learning, the maximum singular value (spectral norm) grows with the number of updates performed by the learning algorithm. We propose spectral regularization, which regularizes the spectral norm, to maintain the spectral properties present at initialization. Our experiments across a wide variety of datasets, architectures and non-stationarities demonstrate that spectral regularization is both effective and insensitive to hyperparameters.
Presenter Bio:
Alex Lewandowski is a PhD student supervised by Dale Schuurmans and Marlos C. Machado at the University of Alberta. His research interest is in understanding scalable continual learning algorithms, with the goal of developing algorithms capable of learning autonomously at every scale.
July 5
Join the journey towards Responsible AI
Katrina Ingram, Ethically Aligned AI
Co-hosted by Technology Alberta
Abstract:
If you're not building responsible AI, what kind of AI are you building? In this provocative session, Katrina Ingram will share her journey from U of A student to entrepreneurial pioneer in the field Responsible AI. She'll cover core issues around ethics, data, privacy and algorithmic bias, as well as bigger societal concerns around the impacts of AI on our work and life. This talk will cover a range of perspectives and offer advice for developers, organizations and end users. It will also touch on some exciting new career opportunities in the field of Responsible AI, including the emerging area of AI audits.
Presenter Bio:
Katrina Ingram is the Founder and CEO of Ethically Aligned AI, a company focused on helping organizations to drive better outcomes in the design, development and deployment of AI systems. A seasoned executive, Katrina has over two decades of experience running both not for profit and corporate organizations in the technology and media sectors as well as experience in the public sector. She is a member of DAMA (data management professionals) and volunteers with several AI ethics organizations. She was named to the 100 Brilliant Women in AI Ethics list. Katrina holds an undergrad in business administration from Simon Fraser University, a master of arts in communications and technology from the University of Alberta and is an IAPP certified information privacy professional (CIPP/C). She combines her love of audio and interest in AI as the host of the podcast, AI4Society Dialogues. Katrina developed Canada's first micro-credential in AI Ethics in partnership with Athabasca University. She currently teaches at the University of Alberta and MacEwan University as a sessional instructor. She is a member of the Calgary Police Services Technology Ethics Committee and recently served as the City of Edmonton's Data Ethics Advisor.
July 3
Special Wednesday Seminar
Learning-augmented algorithms for online optimization and beyond
Nico Christianson, PhD candidate in Computing and Mathematical Sciences at Caltech
Abstract:
Modern AI and ML algorithms can deliver transformative performance improvements for decision-making under uncertainty, where traditional, worst-case algorithms are often too conservative. However, AI and ML lack worst-case guarantees, hindering their deployment to real-world settings like energy systems where safety and reliability are critical. In this talk, I will discuss work on developing machine-learning augmented algorithms with provable performance guarantees, focusing in particular on algorithms and lower bounds for integrating black-box ML “advice” in general online optimization problems. I will also highlight some recent steps toward leveraging uncertainty quantification to improve learning-augmented algorithm performance, as well as applications of our work to energy and sustainable computing.
Presenter Bio:
Nico Christianson is a PhD candidate in Computing and Mathematical Sciences at Caltech, where he is advised by Adam Wierman and Steven Low. Before Caltech, he received his AB in Applied Mathematics from Harvard. He is broadly interested in online algorithms, learning, and optimization, with an emphasis on developing learning-augmented algorithms with provable guarantees for problems spanning energy, carbon-aware computing, and sustainability. Nico’s work is supported by an NSF Graduate Research Fellowship.
June 28
NO SEMINAR
June 21
How to Specify Aligned Reinforcement Learning Objectives
Dr. Brad Knox, Associate Research Professor, University of Texas at Austin
Abstract:
I will discuss how practically to specify reinforcement learning (RL) objectives through careful design of reward functions and discounting. I'll provide tools for diagnosing misalignment in RL objectives, such as finding preference mismatches between the RL objective and human judgments, and examining the indifference point between risky and safe trajectory lotteries. Common pitfalls that can lead to misalignment are highlighted, including naive reward shaping, trial-and-error reward tuning, and improper handling of discount factors. I also sketch best practices for designing interpretable, aligned RL objectives and discuss open problems that hinder the design of aligned RL objectives in practice.
Presenter Bio:
Dr. Brad Knox is a Research Associate Professor of Computer Science at the University of Texas at Austin. His research has largely focused on the human side of reinforcement learning. He is currently concerned with how humans can specify reward functions that are aligned with their interests. Brad’s dissertation, “Learning from Human-Generated Reward”, comprised early pioneering work on human-in-the-loop reinforcement learning and won the 2012 best dissertation award for the UT Austin Department of Computer Science. His postdoctoral research at the MIT Media Lab focused on creating interactive characters through machine learning on puppetry-style demonstrations of interaction. Stepping away from research during 2015–2018, Brad founded and sold his startup Bots Alive, working in the toy robotics sector. In recent years, Brad co-led the Bosch Learning Agents Lab at UT Austin and was a Senior Research Scientist at Google. He has won multiple best paper awards and was named to IEEE Intelligent System’s AI’s 10 to Watch in 2013.
June 14
Video Question-Answering in the Era of LLMs
Dr. Angela Yao, Assistant Professor, National University of Singapore
Abstract:
Video question-answering is an ideal test-bed for evaluating the reasoning capabilities of the latest multi-modal large language models (MLLMs). This talk will take a deep dive into the behaviours of multimodal LLMs for VideoQA. We show that despite their higher QA accuracy, MLLMs share many of the weaknesses of previous non-LLM techniques. For example, they are weak in temporal understanding, visual grounding, and display limited capability of multimodel reasoning. Moreover, despite featuring LLMs, the models are not robust to language variations like question rephrasing. Understanding these limitations is crucial not only for developing future VideoQA techniques but also for integrating MLLMs into everyday applications.
Presenter Bio:
Dr. Angela Yao is an associate professor in the School of Computing at the National University of Singapore. She received a PhD from ETH Zurich and a BASc from the University of Toronto. Angela leads the Computer Vision and Machine Learning group, with a special focus on vision-based human motion analysis. She is the recipient of the German Pattern Recognition (DAGM) award (2018) and Singapore’s National Research Foundation's Fellowship in Artificial Intelligence (2019).
June 12
Special Wednesday Seminar
The Power of Good Old-Fashioned AI for Urban Traffic Control
Dr. Mauro Vallati, Professor, University of Huddersfield, UK
Abstract:
AI approaches are increasingly being used in intelligent urban traffic control techniques, to improve mobility and reduce emissions. While a large number of studies leverage on machine learning techniques, the good old model-based AI is gaining traction. In this talk, we will first look into how urban traffic control is currently performed. Then, we will present a traffic signal optimization approach based on AI planning that is being trialed in the UK, and will discuss how GOFAI can provide useful tools for traffic engineers, domain experts, and practitioners.
Presenter Bio:
Dr. Mauro Vallati is Professor of AI at the University of Huddersfield, UK, where he is the director of the Research Centre on Autonomous and Intelligent Systems. He is an ACM Senior Member, and ACM Distinguished Speaker on artificial intelligence (AI) for the UK. He has extensive experience in real-world applications of AI methods and techniques, spanning from healthcare to train dispatching. Since 2016, he has led several research grants and contracts in the field of urban traffic control, leading to numerous high-impact academic publications, and patents filed in United Kingdom, China, and United States. In 2021 he was awarded a prestigious UKRI Future Leaders Fellowship for investigating AI-based autonomic urban traffic monitoring and control, with the aim of designing intelligent systems that can autonomously recognize the insurgence of traffic congestion and implement traffic light strategies to mitigate its impact on the urban traffic network.
June 10
Special Monday Seminar
Exploring in Sparse-Reward Domains
Dr. Guni Sharon, Assistant Professor, Texas A&M University
Abstract:
Sparse-reward domains pose significant challenges in reinforcement learning (RL) due to the rarity of feedback signals, making it difficult for agents to learn effective policies. This talk delves into the intricacies of exploration in such environments, balancing the need to explore new possibilities with exploiting known rewards—a dilemma known as the explore-exploit tradeoff. Attendees will gain insights into cutting-edge exploration techniques, practical challenges, and innovative solutions, equipping them with the knowledge to tackle sparse-reward problems in their own RL research and applications.
Presenter Bio:
Dr. Guni Sharon is an Assistant Professor at Texas A&M University in the Department of Computer Science & Engineering. His research interests encompass Artificial Intelligence, Intelligent Transportation Systems, Reinforcement Learning, and Combinatorial Optimization. Dr. Sharon has a strong theoretical foundation in AI, particularly in reinforcement learning, combinatorial search, multiagent route assignment, game theory, flow and convex optimization, and multiagent modeling and simulation. He has extensive experience applying these theoretical concepts to practical problems in traffic management and optimization. Committed to bridging theory and practice, Dr. Sharon aims to advance both the applicability of his research to real-world problems and the theoretical frameworks that underpin these solutions.
June 7
HonestDoor: Entrepreneurship and the Journey of Using Data Science to Disrupt Real Estate
Dan Belostotsky, Founder & CEO of HonestDoor
Co-hosted by Technology Alberta
Abstract:
HonestDoor is a technology company with a focus on data in real estate. With Canada’s largest real estate database, it uses AI/ML to estimate home values for all residential properties across Canada. I will be discussing how our company has used this to become a fast-growing site for hundreds of thousands of buyers and sellers. I’ll also discuss the challenges we’ve had both as a company and also in developing our product.
Presenter Bio:
Dan Belostotsky is the founder of the Digital Media company sold to the Pattison Group, founder of HonestDoor.com, investor in multiple tech companies and VC funds, and owner of the real estate company Otto Capital Group Inc.
May 31
NO SEMINAR - Computing Science Center Building Power Shut-down
May 30
Special Thursday Seminar
Evaluation of NLG Systems: From Reaction to Anticipation
Dr. Jackie Chi Kit Cheung, Associate Professor at McGill and Canada CIFAR AI Chair at Mila
Abstract:
Large language models (LLMs) can make factual errors or unsupported claims—sometimes called hallucinations—which can be costly or harmful to the developers, users, and other stakeholders relevant to an NLG system. This type of errors had been anticipated by the NLG research communities years in advance of the release of popular pretrained LLMs, yet they still occur in deployed LLMs. Hallucinations, however, are not the only issue faced by LLMs. In this talk, I ask: how can we anticipate and mitigate potential issues with NLG systems before they become the next embarrassing headline? First, I discuss our work in systematically surveying the recent NLP literature on automatic summarization as a study of how NLP researchers discuss and frame responsible AI issues. Overall, we find that the papers we examined typically do not discuss downstream stakeholders or imagine potential impacts or harms that the summarization system may cause. Next, I present our current efforts to encourage more structured reflection of evaluation practices in NLP, focusing in particular on benchmark design and creation. I introduce our novel framework, Evidence-Centred Benchmark Design, inspired by work in educational assessment.
Presenter Bio:
Dr. Jackie Chi Kit Cheung is an associate professor at McGill University's School of Computer Science, where he co-directs the Reasoning and Learning Lab. He is a Canada CIFAR AI Chair and an Associate Scientific Co-Director at the Mila Quebec AI Institute. His research focuses on topics in natural language generation such as automatic summarization, and on integrating diverse knowledge sources into NLP systems for pragmatic and common-sense reasoning. He also works on applications of NLP to domains such as education, health, and language revitalization. He is motivated in particular by how the structure of the world can be reflected in the structure of language processing systems. He is a consulting researcher at Microsoft Research Montreal.
May 24
NO SEMINAR - UPPER BOUND
May 17
Tracking Changing Probabilities via Dynamic Learners
Dr. Omid Madani, recently, Principal Engineer at Cisco Secure Workload
Abstract:
The world is always changing, and yet may be stable enough for learning to predict with probabilities. Due to change, however, the estimated probabilities need to be modified at times, possibly substantially. In the context of online multiclass probabilistic prediction via finite-memory predictors, we present two moving average techniques, one based on the exponentiated moving average (EMA) and one based on queuing a few count snapshots. We show that the combination, and in particular supporting dynamic predictand-specific learning rates, offers advantages in terms of faster change detection and convergence. In the process, we touch on a variety of topics including internal vs external non-stationarity, stability plasticity dilemma, bias and variance, probabilistic convergence, and the challenges of using log-loss for evaluation when the input stream includes unseen (possibly noise) items, for which we develop approximate propriety. We motivate this task within the framework of prediction games, an approach to self-supervised lifelong cumulative learning of a hierarchy of concepts.
Presenter Bio:
Omid is interested in all aspects of intelligence and mind, especially from a computational perspective. Most recently, he was a founding member of the Tetration Analytics division of Cisco, and led the machine learning efforts at Tetration and Cisco Secure Workload. Prior to Cisco, Omid held research and engineering positions at Google Research (the perception group), SRI, and at Yahoo! Research, developing and applying machine learning to a variety of problems such as web search, video indexing, and network security. Omid received his BS from the University of Houston, and PhD from the University of Washington, and was a Postdoctoral fellow at the University of Alberta in Edmonton, working with Russell Greiner.
May 10
Learning to Rephrase Inputs for Downstream Text Classification
Saeed Najafi, PhD student, University of Alberta
Abstract:
Recent NLP research has developed effective techniques to control or alter the behavior of Pre-trained Language Models (PLMs). However, current PLM control techniques have not considered altering the original input text to improve the performance of the PLMs. We investigate this idea by training a secondary, smaller PLM to paraphrase the original input at training and test time, thus augmenting the existing data and improving model performance. We experiment on six text classification datasets, demonstrating that incorporating paraphrase augmentation during both training and testing phases enhances the performance of discrete/soft prompt optimization and efficient tuning techniques. Finally, we discuss our future work, which aims to extend this learning framework to multi-hop question-answering datasets for complex question decomposition.
Presenter Bio:
Saeed Najafi is a fourth-year PhD student in Computing Science at the University of Alberta, working with Professor Alona Fyshe. He explores various topics, including parameter-efficient optimization, question-answering, and policy optimization within LLMs. Previously, Saeed earned a Master's degree in Computing Science from the University of Alberta and a Bachelor's degree from Amirkabir University of Technology. He has experience working at both small-scale startups and big tech companies, applying various research techniques in applied NLP projects.
May 3
DOCEO AI journey in implementing AI
Ahmad Jawad, CEO of DOCEO (DOKEO) AI, CEO of Intellimedia, Co-founder Edmonton Research Park Business Consortium, and AI champion
Co-hosted by Technology Alberta
Abstract:
As an EdTech software company, we specialize in developing solutions that collect and analyze data on K-12 students to enhance educational practices and support student learning. Currently, we are in the planning phase of integrating AI technology to offer predictive analytics and tailored recommendations. This is aimed to facilitate and augment decision-making processes in both educational planning and student support services. It is important to recognize that schools manage more than just student data; they also handle financial, HR, and feedback data, all of which play a crucial role in influencing student success.
Presenter Bio:
Ahmad Jawad is an established member of the Alberta technology community, having founded and expanded Intellimedia LP and DOCEO AI into a thriving corporation in the EdTech field across Canada that focuses on education analytics, digitized form management in school districts and leveraging AI as a data informed decision making tool to support student learning. Ahmad holds a Bachelor of Science from the University of Alberta, an Executive Master of Business Administration and completed a Management Excellence program at Harvard Business School. Ahmad is a believer in continuous learning. Ahmad speaks three languages: Arabic, English, and French.
Ahmad is a passionate community and industry steward, committing both time and resources to supporting several not-for-profit and industry organizations. Ahmad is on the board of Technology Alberta, board member of the Computer Science Industry Advisory Board at the University of Alberta and Edmonton Regional Innovation Network steering committee. Ahmad is the co-founder and director of the Edmonton Research Park Business Consortium, promoting innovation and collaboration between companies in the Edmonton research park and larger innovation community, and strongly believes in supporting a leading edge ecosystem in Alberta to make it attractive to all talents, innovators and investors throughout Canada.
April 26
A Prototype of an Autonomous Control System using Sound for Reducing Anxiety in ICU Patients
Dr. Martha Steenstrup, Independent
Abstract:
Patients in critical care commonly experience anxiety which can negatively affect both recovery and longer-term health. Sound has proven effective in reducing anxiety and is, in many respects, preferable to conventional pharmacological treatment. In this talk, I describe the design and implementation of and initial experimentation with a prototype of an autonomous control system that employs sound for anxiety reduction and reinforcement learning in patient-appropriate sound selection.
Presenter Bio:
Volunteer dogsbody and wannabe polymath who strives to live lightly on the earth.
April 19
Revisiting Overestimation in Value-based Deep Reinforcement Learning
Prabhat Nagarajan, PhD student, University of Alberta
Abstract:
Since the introduction of Deep Q-networks (DQN), deep reinforcement learning has had several back-to-back advances. One such early advance is Double DQN, which was meant to address the well-known overestimation phenomenon in algorithms such as Q-learning and, consequently, DQN. In light of recent insights, we revisit both DQN and Double DQN. We observe that the optimizer-loss function combination can substantially impact overestimation. Moreover, we explore alternatives to Double DQN where two Q-functions are trained and find that they further reduce overestimation upon Double DQN.
Presenter Bio:
Prabhat Nagarajan is currently a PhD student working with Marlos C. Machado and Martha White. Prior to his PhD, he completed a Master’s in Computer Science at UT Austin, where he researched reproducibility in deep reinforcement learning and preference-based inverse reinforcement learning. His industry research experience includes 3 years at Preferred Networks where he worked on open source deep reinforcement learning and reinforcement learning for robotics. He has also interned at Sony AI, researching efficient methods for reward shaping in reinforcement learning.
April 12
From Low-Rank Adaptation to High-Rank Updates: Training Large Models with Limited Memory
Yongchang Hao, PhD student, University of Alberta
Abstract:
As pre-trained models grow larger, fine-tuning them becomes challenging due to memory constraints. Low-rank adaptation (LoRA) reduces parameters needing fine-tuning but limits update expressiveness. In this presentation, we will analyze the dynamics of LoRA and show it can be approximated by random projections. Based on this observation, we propose our method Flora, which is able to achieve high-rank updates by resampling the projection matrix. Our method has the same space complexity as LoRA while demonstrating superior performance on several benchmarks.
Presenter Bio:
Yongchang Hao is currently a first-year PhD student at the University of Alberta working with Professor Lili Mou. His research interests are broad in machine learning, including language models, reinforcement learning, and optimization. He has published relevant papers at internationally renowned conferences such as NeurIPS, ICLR, ACL, NAACL. Previously, Yongchang obtained a Master's degree from the University of Alberta and a Bachelor's degree from Soochow University. He previously interned at Tencent AI Lab and Google. His long-term research goal is to build compute-efficient large-scale intelligence systems.
April 5
Business Case For AI/ML in Health and Wellness Industry
Mehadi Sayed, President & CEO, Clinisys EMR Inc.
Co-hosted by Technology Alberta
Abstract:
The impact of AI/ML in health and wellness industry has become significantly prominent in the last few years. In this presentation, I will share our company’s journey over the past decade and demonstrate a variety of business cases where the use of AI/ML has made the most impact. I will discuss the challenges, successes, impediments, and even failures encountered by a company such as Clinisys. Finally, I will explore the notable shifts that we are witnessing in the health and wellness domain, drawing upon examples from some of our current projects.
Presenter Bio:
Mehadi Sayed is the founding President and CEO of Clinisys EMR Inc. The company has been operational for over 12 years with its head office located at the Edmonton Research Park. Under Mehadi Sayed's guidance, Clinisys data scientists have worked on numerous projects in the health and wellness domain covering a wide variety of topics, including but not limited to patient re-admission, cancer care resource optimization, and the use of ML in predictive modelling for athlete data.
April 4
Special Thursday Seminar
Explainable Planning and Decision Making
Dr. William Yeoh, Washington University in St.Louis
Abstract:
With increasing proliferation and integration of planning and decision-making systems in our daily life, there is a surge of interest in systems that can explain the reasons for their decisions. In this talk, I will describe such explainable systems through the lens of model reconciliation, which is the problem of reconciling the mental models of the AI system and the human user receiving the explanation. I will also provide an overview of our work in this space, including how logic- and argumentation-based approaches can be used.
Presenter Bio:
William Yeoh is an associate professor in the Department of Computer Science and Engineering and the director of the Division of Computational and Data Sciences at Washington University in St. Louis. His research focus is on AI with the goal of enabling effective human-AI collaboration. He builds on his primary expertise in distributed constraint optimization as well as automated planning and scheduling to develop optimization algorithms for human-aware agent-based systems. He is an NSF CAREER recipient and was named in IEEE's AI's 10-to-Watch list in 2015. He currently serves on the editorial board of the Artificial Intelligence journal, on the IFAAMAS Board of Directors, on the ICAPS Council, and on the SoCS Council.
March 29
NO SEMINAR - UNIVERSITY CLOSED FOR GOOD FRIDAY
March 22
Directions of Curvature as an Explanation for Loss of Plasticity
Alex Lewandowski, PhD student, University of Alberta
Abstract:
I will argue that the Hessian rank, which counts the number of curvature directions, determines the learning ability of a neural network. While randomly initialized neural networks have a high Hessian rank, current learning algorithms reduce the Hessian rank over time. Thus, loss of curvature directions explains loss of plasticity. Lastly, we show that regularizers which prevent loss of plasticity also prevent loss of curvature, motivating a simple distributional regularizer that proves to be effective across the problem settings considered.
Presenter Bio:
Alex Lewandowski is a PhD student supervised by Dale Schuurmans and Marlos C. Machado at the University of Alberta. His research interest is in understanding scalable continual learning algorithms, with the goal of developing algorithms capable of learning autonomously at every scale.
March 15
The AI Crewmate: A Crush, A Crutch, or A Confidant?
Dr. Rajagopalan Srinivasan, University of Alberta & Indian Institute of Technology Madras
Abstract:
Modern-day industry is replete with large socio-technical systems, and people have to interact closely with complex technologies. Traditionally, it has been assumed that operators are the weak links who cause system failure. In this talk, we will explore how AI-based sensors such as eye tracking can offer insights into the operators’ cognition. These enable science-based approaches to study the dynamics in Human-AI teams with numerous applications, such as the design of human-aware interfaces and decision-support systems as well as training protocols.
Presenter Bio:
Dr. Rajagopalan Srinivasan is a Professor of Chemical Engineering and the Head of the American Express Lab for Data Analytics, Risk & Technology (DART Lab) at IIT Madras. He is currently a Visiting Professor at University of Alberta. Raj received his B.Tech from the Indian Institute of Technology Madras and PhD from Purdue University. Raj’s research program is targeted towards developing systems engineering approaches for the design and resilient operation of complex systems. He is a consultant to over 20 well-known companies such as ABB, ExxonMobil, Honeywell, and Shell. His research has been recognized by Best Paper Awards from several journals & conferences. He is an Associate Editor of several journals including PLOS One, Frontiers in Energy Research, and Process Safety and Environmental Protection.
March 8
Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
Fengdi Che, PhD student, University of Alberta
Abstract:
Off-policy value prediction plays a vital role in reinforcement learning. It is crucial for real-world applications and enhances data efficiency during online learning. But divergence caused by the deadly triad, including bootstrapping, function approximation and off-policy learning, has bothered the field for a long time. Our work proves that combining a target network and over-parameterized linear function approximation stabilizes the learning, even with off-policy data. That is, the deadly triad can be eliminated by two simple, common and popular augmentations.
Presenter Bio:
Fengdi Che is a fourth-year Ph.D. student supervised by Rupam Mahmood. Her research interests focus on off-policy reinforcement learning and improvements in policy gradient algorithms. Recently, she has been reading about the learning ability of transformers and welcomes all kinds of discussions.
March 1
Monitored Markov Decision Processes (Mon-MDPs)
Montaser Mohammedalamen, PhD student, University of Alberta
Abstract:
In reinforcement learning (RL), an agent learns to perform a task by interacting with an environment and receiving feedback (a numerical reward) for its actions. However, the assumption that rewards are always observable is often not applicable in real-world problems. For example, the agent may need to ask a human to supervise its actions or activate a monitoring system to receive feedback. There may even be a period of time before rewards become observable, or a period of time after which rewards are no longer given. In other words, there are cases where the environment generates rewards in response to the agent's actions but the agent cannot observe them. In this paper, we formalize a novel but general RL framework --- Monitored MDPs --- where the agent cannot always observe rewards. We discuss the theoretical and practical consequences of this setting, show challenges raised even in toy environments, and propose algorithms to begin to tackle this novel setting. This paper introduces a powerful new formalism that encompasses both new and existing problems.
Presenter Bio:
Montaser (Monta) is a 2nd-year PhD student working with Prof Michael Bowling. Monta's research areas are around how to make agents learn with reward unavailability and how to make agents behave safely and cautiously when facing novel observations. Before joining the University of Alberta, Monta was a Reinforcement Learning (RL) engineer at SonyAI working on Designing a Multi-agent high dynamic environment in a physics simulator and transferring learned policies to the real world.
February 23
NO SEMINAR - U OF A READING WEEK
February 16
An experimentalist’s journey into RL theory: two successes and a failure
Abhishek Naik, PhD Student, University of Alberta
Abstract:
In this talk, I will discuss two new multi-step algorithms for the average-reward formulation. Multi-step methods can be much more sample-efficient than the more prevalent one-step methods. I will begin with a high-level overview of the “ODE approach” to proving the convergence of RL algorithms. I will then outline how I used those theoretical tools to prove the convergence of two algorithms—and to show that a third algorithm of mine can diverge even in the tabular setting. Finally, I will discuss simple experiments that validate the theory.
Presenter Bio:
Abhishek Naik is a Ph.D. candidate working with Rich Sutton. He will soon defend his dissertation on reinforcement learning in continuing (non-episodic) problems using average reward. After his Ph.D., he wants to continue performing AI research in the space industry. Among other things, he loves reading, playing hockey, and watching Formula 1.
February 9
Policy-Guided Heuristic Search
Dr. Levi Lelis, University of Alberta
Abstract:
In this talk, I will present Levin Tree Search (LTS) and some of its variants. LTS is a state-space search algorithm that uses a policy to guide its search. Variants of LTS use both a policy and a heuristic function to guide the search. Algorithms from the Levin family offer guarantees regarding the number of expansions required before finding a solution to search problems. These guarantees depend on the quality of both the policy and the heuristic function guiding the search. The guarantees are important because they offer a loss function---the Levin loss---that allows us to learn policies that minimize the size of the resulting search tree. We will explore learning schemas using neural networks and context models, with the latter offering additional guarantees. Specifically, the parameters of context models optimizing the Levin loss can be derived by solving a convex optimization problem. I will also present some empirical results. In particular, I will show what may be the fastest policy, learned from data, that is able to solve random instances of the Rubik's Cube.
I aim to make this presentation highly accessible, comparable to a lecture from a 300-level undergraduate course in our department. The talk will summarize the findings of three papers, which are listed below, including the paper that received the Distinguished Paper Award at IJCAI'23.
Single-Agent Policy Tree Search with Guarantees. Laurent Orseau, Levi Lelis, Tor Lattimore, and Theophane Weber. In the Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2018.
Policy-Guided Heuristic Search with Guarantees. Laurent Orseau and Levi Lelis. In the Proceedings of the Conference on Artificial Intelligence (AAAI), 2021.
Levin Tree Search with Context Models. Laurent Orseau, Marcus Hutter, and Levi Lelis. In the Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2023.
Presenter Bio:
Dr. Levi Lelis is an Assistant Professor at the University of Alberta, an Amii Fellow, and a CIFAR AI Chair.
February 2
Health Gauge: Innovating in Applied AI/ML Solutions in Digital Health
Randy Duguay, CEO of Health Gauge Inc.
Co-hosted by Technology Alberta
Abstract:
Randy Duguay presents his company and his experience as a founder of an AI/ML & digital health platform software solution provider. Health Gauge has hired a number of U of A grads from the Computing Science Department, and has a number of key connections with the U of A via ST Innovations and the Faculties of Engineering and Medicine. It also has key business partnerships in the United States, through MedWatch Technologies, and in France, with Tech2Heal, and have been continuing to innovate by tapping into the excellent resources at the U of A and NAIT.
Presenter Bio:
Randy Duguay has a B.Sc (Engineering), an M.Eng (Management) degree, as well as completed executive business development courses with Rotman Business School (University of Toronto), and Sloan Business School (MIT). Randy has over 25 years of experience in telecommunications engineering, new technology commercialization, and senior management positions, from large scale to startups. Randy’s experience includes 25 years of experience with TELUS Communications and TELUS Health Solutions, including senior management roles. For over 20 years, he has worked in health solutions and new technology development and in this time has worked with some of the world’s leading technology, software and solutions companies. Current roles and affiliations include: Director, and former CEO, AI/ML Innovations Inc.; Business Advisor, ST Innovations (UofA); Trustee, Glenrose Rehabilitation Hospital Foundation; Director, My Fertility Labs Inc.
January 26
Exploring Methods for Generating and Evaluating Skill Targeted Reading Comprehension Questions
Spencer von der Ohe, PhD student, University of Alberta
Abstract:
There have been many methods proposed to generate reading comprehension questions. However, few allow specific skills to be targeted and there is still a gap in quality between automatically generated and manually created questions. To narrow this gap, we present SoftSkillQG, a new soft-prompt based language model for generating skill targeted reading comprehension questions that does not require manual effort to target new skills. In this presentation, we explore the strengths of SoftSkillQG and how its weaknesses can be addressed.
Presenter Bio:
Spencer von der Ohe is a Computing Science master’s student at the University of Alberta. He is interested in natural language processing and how it can be applied to real world problems. Spencer is supervised by Dr. Alona Fyshe.
January 19
Exploring Creative Paths in DLC Generation
Johor Jara Gonzalez, PhD student, University of Alberta
Abstract:
In the context of video games, Downloadable Content (DLC) refers to additional content or features that can be incorporated into a game after its initial release. In the fields of Automated Game Design (AGD) and Procedural Content Generation (PCG), various approaches have been explored to augment game content. However, no work has attempted to automatically generate DLCs. This talk will cover our concept of how AGD and PCG can be employed to develop compelling DLCs. We’ll specifically focus on extending the existing level structure through level inpainting and generating additional mechanics through a reinforcement learning-based approach.
Presenter Bio:
Johor Jara Gonzalez is a PhD student at the University of Alberta and Alberta Machine Intelligence Institute (Amii). His research interests are focused on computational creativity, and more precisely DLC Generation and Mechanics in Video Games. He has presented at AAAI’s Artificial Intelligence and Interactive Digital Entertainment conference and reviewed for IEEE's Transactions on Games.
January 12
Advances in Data Driven Teleoperation: A synthesis of previous works & our own
Michael Przystupa, PhD student, University of Alberta
Abstract:
Data-driven teleoperation research investigates the application of machine learning models for mapping interactions between control interfaces (e.g., a joystick) and robotic arms to simplify human-robotic interactions. There is a real-world utility for such AI systems in assistive robotics, where people living with a disability rely on robots to complete daily tasks (e.g., opening doors, brushing teeth, etc.). Existing mappings involve cycling between controlling subsets of a robot’s pose. These can be tedious because they can require switching the control mode anywhere from 30 to 60 times to accomplish daily tasks. Data-driven mappings simplify teleoperation by mapping a user's inputs directly to desired robot motions, eliminating the need to switch the control mode. This presentation covers previous works investigating data aspects of such systems, including data collection procedures (supervised vs unsupervised) and choice of data modalities (robotic proprioceptive information, images, text, and belief). The latter half of the presentation discusses our own work explicitly enforcing teleoperation properties and briefly includes incorporating such models with shared autonomy systems. Overall, attendees can expect to learn how to build data-driven teleoperation systems and an introduction to existing research in this application of machine learning.
Presenter Bio:
Michael Przystupa is a 5th year PhD student at the University of Alberta working at the intersection of machine learning and robotics. His research has spanned the applications of deep learning in robotics topics including visual servoing, motor primitives and teleoperation. He is co-supervised by Dr. Martin Jagersand and Dr. Matthew Taylor.
January 5
NO SEMINAR - U OF A WINTER CLOSURE
Page updated
Report abuse