Date: December 30, 2022.

Title: R Workshop: Part I: Visualization , Part II: Advanced R

Instructor: Balasubramanian Narasimhan, Department of Statistics, Stanford University.

Description: The Visualization workshop will lead participants through the powerful graphics capabilities built into R and associated packages. The second part will provide a hands-on experience with the advanced features of R and programming, and touch upon package development.

More Info:

More information can be found here.

Date: December 26, 2022, Morning session

Title: Artificial Intelligence (AI) in Precision and Digital Health

Instructor: Bibhas Chakraborty, Duke-NUS Graduate Medical School and Department of Statistics & Data Science, National University of Singapore

Description: Modern medicine and healthcare acknowledge the fact that “one size does not fit all”. This philosophical shift has given rise to the relatively recent paradigm of personalized or precision medicine/health, which aims to find the right treatment for the right patient. Another area of healthcare, which in its goal and operationalization often overlaps with precision medicine, involves delivering treatments to patients via mobile phone or other digital means, and is known as digital health or mobile health (mHealth). In this course, we will focus on constructing data-driven precision and digital health interventions for chronic, lifestyle diseases and disorders (or preventions thereof, say, via promoting healthy behaviours like exercising), using artificial intelligence (AI)-inspired statistical tools. Such interventions often involve sequential decision making around type, dosage and even timing of treatments. This is where algorithms from reinforcement learning (RL), a sub-domain of AI, become particularly useful. We will discuss two types of sequential treatment rules, namely, dynamic treatment regimes (DTRs) in precision health, and just-in-time adaptive interventions (JITAIs) in mHealth. This course aims to provide a comprehensive presentation of this topic, beginning with an overall introduction including relevant data sources. We will then turn our attention to estimation of the optimal decision rules as well as efficient adaptive experimental designs.

The prerequisites of the course include a thorough grasp of regression analysis and basic understanding of Bayesian statistics and large-sample theory. Demonstrations will be performed using R, so familiarity with R is desirable.

OUTLINE:
This course will be comprised of the following 3 parts:

• Introduction to Precision and Digital Health
• Dynamic Treatment Regimes: Use of AI Algorithms (e.g., Q-learning) for Offline Learning
• Mobile Health Interventions: Use of AI Algorithms (e.g., Thompson Sampling) for Online Learning

Date: December 30, 2022

Title: Introduction to Deep Learning

Instructor: Dr. Abhinanda Sarkar, Great Learning

Description: This short course serves to introduce deep neural networks to statisticians, and also serves as an introduction to the analysis of unstructured data such as images and text.

• Session 1: Overview of machine learning and neural networks, particularly in the context of statistical classification.
• Session 2: The basic mathematics of deep learning using convolutional neural networks for image analysis as an example.
• Session 3: Recurrent neural networks with applications to the analysis of sequential data, such as text and time series.
• Session 4: Survey of recent work connecting deep neural networks to regularization and related methods in statistics.

Prerequisites: Some experience with a statistical programming language such as R or Python, and familiarity with linear and logistic regression.