COVID-19 modelling and applications in the pandemic
Dr. Caroline Colijn
Mathematical modelling has been highly prominent during the pandemic. In this talk I'll describe what COVID-19 models are (at the population level), how they work, and I will introduce several models describing COVID-19 transmission. I will end with perspectives on the next steps for the virus and for our response.
The Hard Path to Transparency and Reproducibility in Cancer Bioinformatics
Dr. Benjamin Haibe-Kains
One of the main challenges in precision oncology consists of developing predictors of drug response to select the most beneficial therapy for each individual patient. In this context, preclinical models are crucial to study the association between molecular features of tumor cells and response to chemical perturbations. However, only few predictors of drug response have been successfully translated to clinical settings. Such a low success rate is due not only to the complexity of the mechanisms underlying anticancer drug response, but also to multiple factors that can be controlled in the research settings. These factors include the inevitable noise in high-throughput biological experiments and the ever-increasing sophistication of the analytical pipelines used to develop predictors of drug response. In this presentation, I will present our attempts to characterize experimental noise, account for it in the predictive modeling and how new software platforms can be used to improve transparency and reproducibility in cancer Bioinformatics.
Dr. Luke Bornn
In this talk I will explore how players perform, both individually and as a team, on a basketball court. By blending advanced spatio-temporal models with geography-inspired mapping tools, we are able to understand player skill far better than either individual tool allows. Using optical tracking data consisting of hundreds of millions of observations, I will demonstrate these ideas by characterizing defensive skill and decision making in NBA players.
Machine Learning Fairness
Dr. Nithum Thain
Fairness is a fundamental consideration in the design and training of machine learning algorithms. We see time and again how even well-intentioned systems designers can inadvertently build bias into their ML models. In this talk we will introduce some of the concepts of the growing field of ML Fairness. We put ourselves in the shoes of someone building an ML algorithm to diagnose disease, and by stepping through the training process, we see how fairness issues might arise. We introduce some of the terms and techniques of fairness before stepping back and discussing the current state of the field.