Evolution of language models, from encoding words to simple vectors to training LLMs. Train and build LLM, understand concepts like self- and cross-attention in LLMs and their applications, review research …
Introduces fundamental concepts of computation, data structures, algorithms, & databases, focusing on their role in data science. Covers both theoretical studies & hands-on learning activities. Includes basic data structures, advanced …
Many problems in data science essentially boil down to some mathematical relationships that are to be solved numerically. But have you ever wondered how computers could do math? This graduate-level …
Covers the fundamental concepts of uncertainty in artificial intelligence (AI). Students will explore various techniques and models used to handle uncertainty in AI and machine learning systems, including Bayesian deep …
Covers the fundamentals of probability and stochastic processes. Students will become conversant in the tools of probability, clearly describing and implementing concepts related to random variables, properties of probability, distributions, …
Explores the mathematical foundations of inferential and prediction frameworks commonly used to learn from data. Frequentist, Bayesian, Likelihood viewpoints are considered. Topics include: principles of estimation, optimality, bias, variance, consistency, …
Introduction to regression modeling. Topics will be discussed first in the context of linear regression, and then revisited in the context of logistic regression, ordinal regression, proportional hazards regression, and …
Introduces physics-aware deep learning (PADL), an emerging approach that embeds physical laws into neural networks for accurate, efficient modeling. Topics include differential equations, physics-informed neural networks, neural operators, and PyTorch …
Fundamentals of data mining and machine learning within a common statistical framework. Topics include boosting, ensembles, Support Vector Machines, model-based clustering, forecasting, neural networks, recommender systems, market basket analysis, and …
Provides an exploration of foundational concepts in modern time series modeling and analysis. The course covers both classical statistical and signal processing methods and contemporary deep learning models.
This course provides the opportunity to offer a new topic in the subject area of data science.
Covers data pipeline: techniques to collect data, organize, query & apply the data, and generate products that describe the insights. Topics include Python environments, containers using Docker, data wrangling with …
Combines topics in data ethics, critical data studies, public policy, governance, and regulation. Address challenges by topic (Health, Education, Culture & Entertainment, Security & Defense, Cities, Environment, Labor). Research how …
Specialized or advanced topics not in DS current course offerings. Requires (a) approval of the program director and (b) an SDS faculty member who will serve as instructor. Propose a …
Graduate-level independent study conducted under the supervision of a specific instructor(s)
The DH Certificate Practicum provides principles for working with humanities materials as data, while maintaining a commitment to humanistic inquiry. Students will learn to integrate digital humanities methods into coursework …
Learning tools and concepts for computing on big data. Learn how to use Spark for large-scale analytics and machine learning. Spark is an open-source, general-purpose computing framework that is scalable …
Covers advanced theoretical concepts for deep neural networks. Topics include convolutional neural networks and their design principles, encoder-decoder architectures, recurrent neural networks, transformers, bounding box detection, image segmentation, generative adversarial …
Current state and future trends in Machine Learning Systems are covered. Topics include hardware systems, software systems, and Machine Learning optimized for metrics beyond predictive accuracy.
Advanced topics within Machine Learning.