Summer 2023
Advanced Concepts of Deep Learning
June 13 and 14, 2023
9 AM to 5 PM both days
G9.102
This course will provide an introduction to key and emerging concepts and ideas in deep learning. The 1st part of this course will introduce the design and principle behind recent advances in model architecture: transformers (including several efficient transformer designs), graph neural networks, and several other new architectures that utilize attention-like multiplicative updates. The 2nd part of this course will cover mathematics and algorithms of generative probabilistic modeling with deep learning, including energy-based models, variational autoencoder, generative adversarial network, normalizing flow, neural ODE, and diffusion probabilistic models. Conceptual advances will be the focus of this nanocourse. You are encouraged to bring a modeling problem of interest for the group discussion session.
NOTE: This course is advanced and requires basic knowledge of programming, machine learning, and deep learning.
Registration closed, nanocourse full.
Applications are open to any person at UTSW or in the surrounding community who are interested in learning about advancements in deep learning. Class space is limited. Responses to the registration questions will be reviewed and acceptance in the course will be determined from the best match between participant experience and benefit derived from the training and the course content. Decisions will be conferred via email.
For UTSW graduate students and trainees, academic credit (1 credit hour) is available.
Graduate students use Special Topics - Advanced Concepts of Deep Learning (exact course number TBA),
Postdocs use PDRT 5095-01 Special Topics in Bioinformatics - Advanced Concepts of Deep Learning.
Graduate students and postdocs are REQUIRED to submit supervisor endorsement form before 6/10/2023, if accepted into the nanocourse.
Instructor: Jian Zhou, PhD
Have you ever wanted to design a biological system of your interest? The opportunity to do so is now at your fingertips! Try L++, a new programming language for biologists that can intuitively and efficiently model multi-resolution biological systems ranging from a set of reactions to whole organisms.
Creating detailed, accurate virtual organisms has often been a subject of science fiction. Now, for the first time, programmers and scientists alike will have the opportunity to experience modeling and building a life form on their own as they learn to design virtual life. The course will focus on the L++ programming language and creating biologically realistic virtual organisms. The goal of this course is to introduce students to features unique to L++ as a programming language and give them hands-on practice in programming life. Students will learn how to read and write basic L++ code in addition to programming models with spatial context and designing simulations of cellular processes including bacterial chemotaxis and bacterial cell division. This course will equip you with skills essential for the future of biological research.
Day 1: Introduction to L++, Bacterial Chemotaxis Programming
Day 2: E. coli Cell Division Programming, Perturbation of E. coli
Prerequisites: some familiarity with the basics of biology, no programming background required.
Registration closed, nanocourse full.
Applications are open to any person at UTSW or in the surrounding community who are interested in learning about advancements in life sciences. Class space is limited. Responses to the registration questions will be reviewed and acceptance in the course will be determined from the best match between participant experience and benefit derived from the training and the course content. Decisions will be conferred via email.
For UTSW graduate students and trainees, academic credit (1 credit hour) is available.
Graduate students use Special Topics - L++: a programming language for building and executing in silico organisms (exact course number TBA).
PostDocs use PDRT 5095-02 Special Topics in Bioinformatics - L++: a programming language for building and executing in silico organisms.
Graduate students and postdocs are REQUIRED to submit a supervisor endorsement form before 6/17/2023, if accepted into the nanocourse.
Instructors: Daehwan Kim, PhD and Donghoon Lee, PhD
TA: Chanhee Park