Collaborating Authors


AI: The Tool, Not the Movie


"The development of full artificial intelligence (AI) could spell the end of the human race. It would take off on its own and re-design itself at an ever increasing rate. Humans, who are limited by slow biological evolution, couldn't compete and would be superseded." Now, I love Stephen Hawking and his way of thinking. Here is a person who seems able to look around corners to predict the future. And I just don't buy this statement.

KDD: Graph neural networks, fairness, and inclusivity


As general chair of this year's ACM Conference on Knowledge Discovery and Data Mining (KDD), Huzefa Rangwala, a senior manager at the Amazon Machine Learning Solutions Lab, has a broad view of the topics under discussion there. Two of the most prominent, he says, are graph neural networks and fairness in AI. Graphs are data representations that can encode relationships between different data items, and graph neural networks are machine learning models that are useful for knowledge discovery because they can be used to infer graph structures. "Our world is connected in lots of ways, so you'll see graph neural networks find applications in lots of different domains, all the way from social networks and transportation networks to knowledge graphs and drug discovery," Rangwala says. The Amazon Machine Learning Solutions Lab brings the expertise of Amazon scientists and the resources of Amazon Web Services to bear on customers' machine learning problems.

Yoga Pose Classification With TensorFlow's MoveNet Model


Since the beginning of the Covid-19 pandemic, the online fitness trend has exploded. That's led to a surge of research into interactive AI coaches to offer user's an interactive experience in the comfort of their homes. This article describes the first phase of developing an AI yoga instructor that can view the user's alignment and recommend adjustments to improve their postures and, therefore, prevent injuries. During the first phase of the project, the goal is to find a model that produces the best accuracy score for correctly identifying five yoga poses: Warrior 2, Downward Facing Dog, Goddess, Plank, and Tree. Consisting of 1,547 images split into 5 classes, or poses, this dataset is smaller and contains less poses than will be necessary for later phases of the project.

Andrew Watson, Vice President of AI and R & D at Healx – Interview Series


Andrew Watson is Vice President of AI and R & D at Healx. Prior to joining Healx he worked at the technology giant Dyson, where he was the founding member of the Machine Learning Research Department, leading the research and implementation of machine learning and artificial intelligence across a variety of global product categories. In his time as Director of Machine Learning at Dyson, Andrew also established a new research group, focused on the intersection between machine learning and cutting-edge biomedical research. Healx is an AI-powered, patient-inspired technology company, dedicated to helping rare disease patients around the world access life-improving therapies. There are 7,000 known rare diseases that affect 400 million people across the globe but only 5% of those conditions have approved treatments.

Deep learning methods to predict amyotrophic lateral sclerosis disease progression - Scientific Reports


Amyotrophic lateral sclerosis (ALS) is a highly complex and heterogeneous neurodegenerative disease that affects motor neurons. Since life expectancy is relatively low, it is essential to promptly understand the course of the disease to better target the patient’s treatment. Predictive models for disease progression are thus of great interest. One of the most extensive and well-studied open-access data resources for ALS is the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) repository. In 2015, the DREAM-Phil Bowen ALS Prediction Prize4Life Challenge was held on PRO-ACT data, where competitors were asked to develop machine learning algorithms to predict disease progression measured through the slope of the ALSFRS score between 3 and 12 months. However, although it has already been successfully applied in several studies on ALS patients, to the best of our knowledge deep learning approaches still remain unexplored on the ALSFRS slope prediction in PRO-ACT cohort. Here, we investigate how deep learning models perform in predicting ALS progression using the PRO-ACT data. We developed three models based on different architectures that showed comparable or better performance with respect to the state-of-the-art models, thus representing a valid alternative to predict ALS disease progression.

U-M receives NSF grant for data-driven drug discovery


The Center for Data-Driven Drug Development and Treatment Assessment — to be known as DATA — will support the use of machine learning and …

Computational methods can lead to better vaccines faster – Health Lab Blog


With the support of various machine learning methods, many RV and SV approaches have been developed and applied to COVID-19 vaccine design.

Machine Learning At The Forefront Of Telemental Health


Michael Stefferson received his PhD in Physics from the University of Colorado before deciding to make the jump into machine learning (ML). He spent the last several years as a Machine Learning Engineer at Manifold, where he first started working on projects in the healthcare industry. Recently, Stefferson joined the team at Cerebral as a Staff Machine Learning Engineer and hopes to leverage data to make clinical improvements for patients that will improve their lives in meaningful ways. Here, he talks about use cases, best practices, and what he has learned along his journey into the field of ML. What is your background and how did you first get into machine learning?

The Download: AI to predict ice, and healthcare censorship in China

MIT Technology Review

The news: Researchers have used deep learning to model more precisely than ever before how ice crystals form in the atmosphere. Their paper, published this week in PNAS, hints at the potential to significantly increase the accuracy of weather and climate forecasting. How they did it: The researchers used deep learning to predict how atoms and molecules behave. First, models were trained on small-scale simulations of water molecules to help them predict how electrons in atoms interact. The models then replicated those interactions on a larger scale, with more atoms and molecules.

Moving from ImageNet to RadImageNet for Improved Transfer Learning and Generalizability


See also the article by Mei et al in this issue. Alexandre Cadrin-Chênevert, MD, BEng, is a diagnostic and interventional radiologist at CISSS Lanaudière and clinical professor at Laval University. He has previously served as chief of the medical imaging department. As a Kaggle competition master, he has successfully participated in many machine learning competitions. He is an early member of the Canadian Association of Radiologists (CAR) Artificial Intelligence (AI) Standing Committee. His current research interests include deep learning, computer vision, object detection, self-supervised learning, model generalizability, and public medical imaging datasets.