AI for Statistical Learning

STAT 6393V-001: Topics Course in Statistics

Dates: M/T/W/T/F 1245-1415 in Summer 1

Prerequisites: None; any undergrad level stats course will be a bonus

Textbooks: (Recommended)

  • Bishop & Bishop. Deep Learning: Foundations and Concepts. link

  • Sigrid Keydana. Deep Learning and Scientific Computing with R torch. link

  • Kevin Patrick Murphy. Probabilistic Machine learning: An Introduction. link

Software tools: R, Google Colab, Git. While the course will be taught primarily in R, students can use Python or Julia for their workflows, since the topics covered will be largely platform agnostic.

For more info, email r e e t a m m [a] u a r k [dot] e d u

Course Description

This is an intermediate course on using neural networks for statistical learning. Neural networks/deep learning are the most important class of models in the field of artificial intelligence; the modern technology stack relies heavily on it, and it is ubiquitous in both academia and industry, from weather prediction models to spam filters to personalized medicine. This course explores the synergy between statistics and deep learning and how a) neural networks can augment classical statistical techniques for modeling complex phenomena, and b) statistical inference can make AI models more robust and explainable.

Students will be provided a crash course in distribution theory, statistical inference, and R. Details regarding loss functions and optimization will be covered which are widely applicable to any modern machine learning approach. Students will also be introduced to advanced topics like Bayesian neural networks, simulation-based inference, and uncertainty quantification.

An AI4Stats short course conducted in Fall 2025 at the University of Maryland, Baltimore County, originally covered several of the ideas that underpin this course, but was tailored towards an audience that was already familiar with statistics, or deep learning, or both.

Course Schedule

Week 1: Probability and distribution theory; frequentist and Bayesian methods

Week 2: Loss functions and numerical optimization; building deep learning models in R

Week 3: Custom loss functions; regression and classification; parameter and density estimation

Week 4: Bayesian neural networks; conformal prediction; (deep) Gaussian processes

Week 5: Simulation-based inference; generative modeling

Grading criteria

Your final grades will depend on:

  • Weekly reports that summarize and interpret solutions to problems that you work on in class (graded on completion)

  • A final group project (graded on merit based on a rubric that will be provided)

Generative AI use policy

I will consider distributing course materials to a third party without my authorization a violation of my intellectual property rights and/or copyright law as well as a violation of the U of A’s academic integrity policy. The use of generative artificial intelligence tools in any capacity while completing academic work that is submitted for credit, independently or collaboratively, will be considered academic dishonesty in this course. This includes uploading course materials to AI assistants/agents/websites. Continued enrollment in this class signifies your intent to abide by the policy. Any violation will be reported to the Office of Academic Initiatives and Integrity.