Narges Armanfard

Biography

Narges Armanfard (PhD, PEng) is the Founder and Principal Investigator of McGill University’s iSMART Lab. She's a tenure-track Assistant professor in the Department of Electrical and Computer Engineering at McGill and an Associate Academic member at Mila – Quebec Artificial Intelligence Institute.

Armanfard is also affiliated with McGill’s Centre for Intelligent Machines (CIM), the McGill initiative in Computational Medicine (MiCM), and the McGill Institute for Aerospace Engineering (MIAE).

Her research focuses on developing innovative algorithms for various domains, such as time-series data analysis, computer vision, reinforcement learning and representation learning for tasks like data clustering, classification and anomaly detection.

Her contributions to the field of AI have been recognized with numerous awards from a variety of institutions, including the Natural Sciences and Engineering Research Council of Canada, AgeWell, Vanier-Banting and the Fonds de recherche du Québec, as well as McMaster University, McGill University, the University of Toronto, the Canadian Institutes of Health Research and Scale AI.

Current Students

Cormac Cureton

Master's Research - McGill University

Website

Navid hassan Zadeh

PhD - McGill University

Khanh Ho Ho

PhD - McGill University

Hadi Hojjati

PhD - McGill University

Alexander Koran

PhD - McGill University

Thomas Lai

PhD - McGill University

Brian MacDonald

Master's Research - McGill University

Dario Morle

PhD - McGill University

Abhijeet Praveen

Master's Research - McGill University

Aman Sidhu

Master's Research - McGill University

PhD - McGill University

Jack Wei

Master's Research - McGill University

Publications

Unveiling the Flaws: A Critical Analysis of Initialization Effect on Time Series Anomaly Detection

Alex Koran

Hadi Hojjati

Deep learning for time-series anomaly detection (TSAD) has gained significant attention over the past decade. Despite the reported improveme… (see more)nts in several papers, the practical application of these models remains limited. Recent studies have cast doubt on these models, attributing their results to flawed evaluation techniques. However, the impact of initialization has largely been overlooked. This paper provides a critical analysis of the initialization effects on TSAD model performance. Our extensive experiments reveal that TSAD models are highly sensitive to hyperparameters such as window size, seed number, and normalization. This sensitivity often leads to significant variability in performance, which can be exploited to artificially inflate the reported efficacy of these models. We demonstrate that even minor changes in initialization parameters can result in performance variations that overshadow the claimed improvements from novel model architectures. Our findings highlight the need for rigorous evaluation protocols and transparent reporting of preprocessing steps to ensure the reliability and fairness of anomaly detection methods. This paper calls for a more cautious interpretation of TSAD advancements and encourages the development of more robust and transparent evaluation practices to advance the field and its practical applications.

2024-08-13

ArXiv (preprint)

Forward-Backward Knowledge Distillation for Continual Clustering

Mohammadreza Sadeghi

Zihan Wang

Unsupervised Continual Learning (UCL) is a burgeoning field in machine learning, focusing on enabling neural networks to sequentially learn … (see more)tasks without explicit label information. Catastrophic Forgetting (CF), where models forget previously learned tasks upon learning new ones, poses a significant challenge in continual learning, especially in UCL, where labeled information of data is not accessible. CF mitigation strategies, such as knowledge distillation and replay buffers, often face memory inefficiency and privacy issues. Although current research in UCL has endeavored to refine data representations and address CF in streaming data contexts, there is a noticeable lack of algorithms specifically designed for unsupervised clustering. To fill this gap, in this paper, we introduce the concept of Unsupervised Continual Clustering (UCC). We propose Forward-Backward Knowledge Distillation for unsupervised Continual Clustering (FBCC) to counteract CF within the context of UCC. FBCC employs a single continual learner (the ``teacher'') with a cluster projector, along with multiple student models, to address the CF issue. The proposed method consists of two phases: Forward Knowledge Distillation, where the teacher learns new clusters while retaining knowledge from previous tasks with guidance from specialized student models, and Backward Knowledge Distillation, where a student model mimics the teacher's behavior to retain task-specific knowledge, aiding the teacher in subsequent tasks. FBCC marks a pioneering approach to UCC, demonstrating enhanced performance and memory efficiency in clustering across various tasks, outperforming the application of clustering algorithms to the latent space of state-of-the-art UCL algorithms.

2024-05-29

ArXiv (preprint)

AI healthcare research: Pioneering iSMART Lab

Dr Narges Armanfard, Professor, talks us through the AI healthcare research at McGill University which is spearheading a groundbreaking init… (see more)iative – the iSMART Lab. Access to high-quality healthcare is not just a fundamental human right; it is the bedrock of our societal wellbeing, with the crucial roles played by doctors, nurses, and hospitals. Yet, healthcare systems globally face mounting challenges, particularly from aging populations. Dr Narges Armanfard, affiliated with McGill University and Mila Quebec AI Institute in Montreal, Canada, has spearheaded a groundbreaking initiative – the iSMART Lab. This laboratory represents a revolutionary leap into the future of healthcare, with its pioneering research in AI for health applications garnering significant attention. Renowned for its innovative integration of AI across diverse domains, iSMART Lab stands at the forefront of harnessing Artificial Intelligence to elevate and streamline health services.

2024-04-09

Open Access Government (published)

Self-supervised anomaly detection in computer vision and beyond: A survey and outlook.

Hadi Hojjati

Thi Kieu Khanh Ho

2024-04-01

Neural Networks (published)

Graph-Jigsaw Conditioned Diffusion Model for Skeleton-Based Video Anomaly Detection

Ali Karami

Thi Kieu Khanh Ho

Skeleton-based video anomaly detection (SVAD) is a crucial task in computer vision. Accurately identifying abnormal patterns or events enabl… (see more)es operators to promptly de-tect suspicious activities, thereby enhancing safety. Achieving this demands a comprehensive understanding of human motions, both at body and region levels, while also accounting for the wide variations of performing a single action. However, existing studies fail to simultaneously address these crucial properties. This paper introduces a novel, practical, and lightweight framework, namely Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection (GiCiSAD) to overcome the challenges associated with SVAD. GiCiSAD consists of three novel modules: the Graph Attention-based Forecasting module to capture the spatio-temporal dependencies inherent in the data, the Graph-level Jigsaw Puzzle Maker module to distinguish subtle region-level discrepancies between normal and abnormal motions, and the Graph-based Conditional Diffusion model to generate a wide spectrum of human motions. Extensive experiments on four widely used skeleton-based video datasets show that GiCiSAD outperforms existing methods with significantly fewer training parameters, establishing it as the new state-of-the-art.

2024-03-18

ArXiv (preprint)

Neural network prediction of the effect of thermomechanical controlled processing on mechanical properties

Sushant Sinha

Denzel Guye

Xiaopin Ma

Kashif Rehman

S. Yue

2024-03-01

Machine Learning with Applications (published)

Deep Reinforcement Learning in Human Activity Recognition: A Survey and Outlook.

Bahareh Nikpour

Dimitrios Sinodinos

Human activity recognition (HAR) is a popular research field in computer vision that has already been widely studied. However, it is still a… (see more)n active research field since it plays an important role in many current and emerging real-world intelligent systems, like visual surveillance and human-computer interaction. Deep reinforcement learning (DRL) has recently been used to address the activity recognition problem with various purposes, such as finding attention in video data or obtaining the best network structure. DRL-based HAR has only been around for a short time, and it is a challenging, novel field of study. Therefore, to facilitate further research in this area, we have constructed a comprehensive survey on activity recognition methods that incorporate DRL. Throughout the article, we classify these methods according to their shared objectives and delve into how they are ingeniously framed within the DRL framework. As we navigate through the survey, we conclude by shedding light on the prominent challenges and lingering questions that await the attention of future researchers, paving the way for further advancements and breakthroughs in this exciting domain.

2024-02-19

IEEE Transactions on Neural Networks and Learning Systems (published)

Deep Reinforcement Learning in Human Activity Recognition: A Survey and Outlook.

Bahareh Nikpour

Dimitrios Sinodinos

2024-02-19

IEEE Transactions on Neural Networks and Learning Systems (published)