Upcoming Seminars
Regular Friday Seminars - attending in-person - RSVP here
Pizza by RSVP only
May 10
Learning to Rephrase Inputs for Downstream Text Classification
Saeed Najafi, PhD student, University of Alberta
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
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.
Add event to calendar
May 17
Tracking Changing Probabilities via Dynamic Learners
Dr. Omid Madani, recently, Principal Engineer at Cisco Secure Workload
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
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.
Add event to calendar
May 24
NO SEMINAR - UPPER BOUND
May 30
Special Thursday Seminar
Title TBA
Dr. Jackie Cheung, Associate Professor at McGill and Canada CIFAR AI Chair at Mila
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
May 31
Title TBA
Alex Lewandowski, PhD student, University of Alberta
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
June 7
Title TBA
Speaker TBA
Co-hosted by Technology Alberta
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
June 10
Special Monday Seminar
Title TBA
Dr. Guni Sharon, Assistant Professor, Texas A&M University
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
June 12
Special Wednesday Seminar
Title TBA
Dr. Mauro Vallati, Professor, University of Huddersfield
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
June 14
Title TBA
Dr. Angela Yao, Assistant Professor, National University of Singapore
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
June 21
How to Specify Aligned Reinforcement Learning Problems
Dr. Brad Knox, Associate Research Professor, University of Texas at Austin
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
June 28
Title TBA
Speaker TBA
Location: University of Alberta, Computing Science Centre, Room 3-33
Zoom link here (password: Spr!ng2023)
Abstract:
TBA
Presenter Bio:
TBA
Calendar links coming soon!
More dates coming soon!