Publications

256 Patient-Specific Pre-Treatment Nuclei Size Distribution is of Significance for Post Radiation Therapy Locoregional Recurrence and Survival Outcomes
Yujing Zou
Magali Lecavalier-Barsoum
Manuela Pelmus
Farhad Maleki
Shirin A. Enger
2023-09-01
Radiotherapy and Oncology (published)
doi.org
259 Development of a Cost-Efficient Scintillation-Fiber Detector for Use in Automated Synthesis of Positron Emission Tomography Radiotracers
Hailey Ahn
Liam Carroll
Robert Hopewell
I-Huang Tsai
Shirin A. Enger
2023-09-01
Radiotherapy and Oncology (published)
doi.org
Impact of a vaccine passport on first-dose SARS-CoV-2 vaccine coverage by age and area-level social determinants of health in the Canadian provinces of Quebec and Ontario: an interrupted time series analysis
Jorge Luis Flores Anato
Huiting Ma
M. Hamilton
Yiqing Xia
Sam Harper
David Buckeridge
Marc Brisson
Michael P. Hillmer
Kamil A. Malikov
Aidin Kerem
Reed Beall
Caroline E Wagner
Étienne Racine
S. Baral
Ève Dubé
Sharmistha Mishra
Mathieu Maheu‐giroux
2023-09-01
CMAJ Open (published)
doi.org
Integrating equity, diversity and inclusion throughout the lifecycle of AI within healthcare: a scoping review protocol
Milka Nyariro
Elham Emami
Pascale Caidor
Samira Abbasgholizadeh-Rahimi
2023-09-01
BMJ Open (published)
doi.org
Online Bayesian Optimization of Nerve Stimulation
Lorenz Wernisch
Tristan Edwards
Antonin Berthon
Olivier Tessier-Lariviere
Elvijs Sarkans
Myrta Stoukidi
Pascal Fortier-Poisson
Max Pinkney
Michael Thornton
Catherine Hanley
Susannah Lee
Joel Jennings
Ben Appleton
Philip Garsed
Bret Patterson
Buttinger Will
Samuel Gonshaw
Matjaž Jakopec
Sudhakaran Shunmugam
Jorin Mamen … (see 4 more)
Aleksi Tukiainen
Guillaume Lajoie
Oliver Armitage
Emil Hewage
2023-09-01
bioRxiv (preprint)
doi.org
PP02  Presentation Time: 4:39 PM
Maryam Rahbaran
Jonathan Kalinowski
James Man Git Tsui
Joseph DeCunha
Kevin Croce
Brian Bergmark
Philip Devlin
Shirin A. Enger
2023-09-01
Brachytherapy (published)
doi.org
Saturday, June 24, 20238:30 AM - 9:30 AMMSOR01 Presentation Time: 8:30 AM
Mélodie Cyr
N. Chabaytah
Joud Babik
Behnaz Behmand
Shirin A. Enger
2023-09-01
Brachytherapy (published)
doi.org
WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series
Jean-Christophe Gagnon-Audet
Kartik Ahuja
Mohammad Javad Darvishi Bayazi
Pooneh Mousavi
Guillaume Dumas
Irina Rish
2023-09-01
TMLR (accepted)
openreview.net
openreview.net
Effective Test Generation Using Pre-trained Large Language Models and Mutation Testing
Arghavan Moradi Dakhel
Amin Nikanjam
Vahid Majdinasab
Foutse Khomh
Michel C. Desmarais
One of the critical phases in software development is software testing. Testing helps with identifying potential bugs and reducing maintenan… (see more)ce costs. The goal of automated test generation tools is to ease the development of tests by suggesting efficient bug-revealing tests. Recently, researchers have leveraged Large Language Models (LLMs) of code to generate unit tests. While the code coverage of generated tests was usually assessed, the literature has acknowledged that the coverage is weakly correlated with the efficiency of tests in bug detection. To improve over this limitation, in this paper, we introduce MuTAP for improving the effectiveness of test cases generated by LLMs in terms of revealing bugs by leveraging mutation testing. Our goal is achieved by augmenting prompts with surviving mutants, as those mutants highlight the limitations of test cases in detecting bugs. MuTAP is capable of generating effective test cases in the absence of natural language descriptions of the Program Under Test (PUTs). We employ different LLMs within MuTAP and evaluate their performance on different benchmarks. Our results show that our proposed method is able to detect up to 28% more faulty human-written code snippets. Among these, 17% remained undetected by both the current state-of-the-art fully automated test generation tool (i.e., Pynguin) and zero-shot/few-shot learning approaches on LLMs. Furthermore, MuTAP achieves a Mutation Score (MS) of 93.57% on synthetic buggy code, outperforming all other approaches in our evaluation. Our findings suggest that although LLMs can serve as a useful tool to generate test cases, they require specific post-processing steps to enhance the effectiveness of the generated test cases which may suffer from syntactic or functional errors and may be ineffective in detecting certain types of bugs and testing corner cases PUTs.
2023-08-31
ArXiv (preprint)
doi.org
arxiv.org
Learning Lyapunov-Stable Polynomial Dynamical Systems Through Imitation
Amin Abyaneh
Hsiu-Chin Lin
Imitation learning is a paradigm to address complex motion planning problems by learning a policy to imitate an expert's behavior. However, … (see more)relying solely on the expert's data might lead to unsafe actions when the robot deviates from the demonstrated trajectories. Stability guarantees have previously been provided utilizing nonlinear dynamical systems, acting as high-level motion planners, in conjunction with the Lyapunov stability theorem. Yet, these methods are prone to inaccurate policies, high computational cost, sample inefficiency, or quasi stability when replicating complex and highly nonlinear trajectories. To mitigate this problem, we present an approach for learning a globally stable nonlinear dynamical system as a motion planning policy. We model the nonlinear dynamical system as a parametric polynomial and learn the polynomial's coefficients jointly with a Lyapunov candidate. To showcase its success, we compare our method against the state of the art in simulation and conduct real-world experiments with the Kinova Gen3 Lite manipulator arm. Our experiments demonstrate the sample efficiency and reproduction accuracy of our method for various expert trajectories, while remaining stable in the face of perturbations.
2023-08-30
robot-learning.org/CoRL/2023/Conference (poster)
doi.org
openreview.net
Beyond the ML Model: Applying Safety Engineering Frameworks to Text-to-Image Development
Shalaleh Rismani
Renee Shelby
Andrew J Smart
Renelito Delos Santos
AJung Moon
Negar Rostamzadeh
Identifying potential social and ethical risks in emerging machine learning (ML) models and their applications remains challenging. In this … (see more)work, we applied two well-established safety engineering frameworks (FMEA, STPA) to a case study involving text-to-image models at three stages of the ML product development pipeline: data processing, integration of a T2I model with other models, and use. Results of our analysis demonstrate the safety frameworks – both of which are not designed explicitly examine social and ethical risks – can uncover failure and hazards that pose social and ethical risks. We discovered a broad range of failures and hazards (i.e., functional, social, and ethical) by analyzing interactions (i.e., between different ML models in the product, between the ML product and user, and between development teams) and processes (i.e., preparation of training data or workflows for using an ML service/product). Our findings underscore the value and importance of examining beyond an ML model in examining social and ethical risks, especially when we have minimal information about an ML model.
2023-08-29
Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society (published)
doi.org
arxiv.org
Policy composition in reinforcement learning via multi-objective policy optimization
Shruti Mishra
Ankit Anand
Jordan Hoffmann
Nicolas Heess
Martin A. Riedmiller
Abbas Abdolmaleki
Doina Precup
We enable reinforcement learning agents to learn successful behavior policies by utilizing relevant pre-existing teacher policies. The teach… (see more)er policies are introduced as objectives, in addition to the task objective, in a multi-objective policy optimization setting. Using the Multi-Objective Maximum a Posteriori Policy Optimization algorithm (Abdolmaleki et al. 2020), we show that teacher policies can help speed up learning, particularly in the absence of shaping rewards. In two domains with continuous observation and action spaces, our agents successfully compose teacher policies in sequence and in parallel, and are also able to further extend the policies of the teachers in order to solve the task. Depending on the specified combination of task and teacher(s), teacher(s) may naturally act to limit the final performance of an agent. The extent to which agents are required to adhere to teacher policies are determined by hyperparameters which determine both the effect of teachers on learning speed and the eventual performance of the agent on the task. In the humanoid domain (Tassa et al. 2018), we also equip agents with the ability to control the selection of teachers. With this ability, agents are able to meaningfully compose from the teacher policies to achieve a superior task reward on the walk task than in cases without access to the teacher policies. We show the resemblance of composed task policies with the corresponding teacher policies through videos.
2023-08-29
ArXiv (preprint)
doi.org
arxiv.org