INTRODUCTION TO DEEP LEARNING AND GENERATIVE MODELS

STAT 453

Course Description

Deep learning is a field that specializes in discovering and extracting intricate structures in large, unstructured datasets for parameterizing artificial neural networks with many layers. Since deep learning has pushed the state-of-the-art in many research and application areas, it's become indispensable for modern technology. Focuses on a understanding deep, artificial neural networks by connecting it to related concepts in statistics. Beyond covering deep learning models for predictive modeling, focus on deep generative models. Besides explanations on a mathematical and conceptual level, emphasize the practical aspects of deep learning. Open-source computing provides hands-on experience for implementing deep neural nets, working on supervised learning tasks, and applying generative models for dataset synthesis.

Prerequisties

MATH 320 , MATH 321 , MATH 340 , MATH 341 , MATH 375 , graduate/professional standing, or declared in Statistics VISP

Satisfies

This course does not satisfy any prerequisites.

Credits

Offered

Not Applicable

Grade Point Average

3.61

3.12% from Historical

Completion Rate

100%

0.97% from Historical

A Rate

42.35%

-11.48% from Historical

Class Size

22.01% from Historical

Instructors (2025 Fall)

Sorted by ratings from Rate My Professors

Similar Courses

MACHINE LEARNING IN PHYSICS

PHYSICS 361

A detailed introduction to the use of machine learning techniques in physics. Topics will include basics of probability theory and statistics, basics of function fitting and parameter inference, basics of optimization, and machine learning techniques. A selection of physics topics that are particularly amenable to analysis using machine learning will be discussed. These might include processing collider data, classifying astronomical images, solving the Ising model, parameter estimation from physics data sets, learning physical probability distributions, finding string theory compactifications, and finding symbolic physical laws.

THEORETICAL FOUNDATIONS OF MACHINE LEARNING

COMPSCI/ECE/STAT 861

Advanced mathematical theory and methods of machine learning. Statistical learning theory, Vapnik-Chevronenkis Theory, model selection, high-dimensional models, nonparametric methods, probabilistic analysis, optimization, learning paradigms.

LEARNING BASED METHODS FOR COMPUTER VISION

BMI/COMPSCI 771

Addresses the problems of representation and reasoning for large amounts of visual data, including images and videos, medical imaging data, and their associated tags or text descriptions. Introduces deep learning in the context of computer vision. Covers topics on visual recognition using deep models, such as image classification, object detection, human pose estimation, action recognition, 3D understanding, and medical image analysis. Emphasizes the design of vision and learning algorithms and models, as well as their practical implementations. Strongly recommended to have knowledge in computer vision or machine learning [such asCOMP SCI 540] or medical image analysis [such as B M I /COMP SCI/B M I 567].

ADVANCED DEEP LEARNING

COMPSCI 762

Explore methods and applications of deep learning. Covers cutting-edge topics, including neural architecture design, robustness and reliability of deep learning, learning with less supervision, lifelong machine learning, deep generative modeling, theoretical understanding of deep learning, and interpretable deep learning.

THEORY & ALGORITHMS FOR DATA SCIENCE

COMPSCI 541

Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.