This course explores Natural Language Processing (NLP), examining how computers are trained to understand and process human language. Students will gain a thorough understanding of both core NLP concepts and advanced techniques, including text analysis, language modeling, machine translation, question answering, text generation, conversation modeling, and the latest advancements in large language models.

This course focuses on the core principles of RL. Like statistical learning, a central challenge of RL is to generalize learned capabilities to unseen environments. However, RL faces additional challenges such as exploration-exploitation tradeoff, credit assignment, and distribution mismatch between behavior and target policies. Throughout the course, we will delve into various solutions to these challenges and provide theoretical justifications.

This course provides an overview of the state of the art in software analysis including static and dynamic analysis techniques and verification and validation. It explores the various ways that the analyses are used to predict software behavior. The applications include inference, symbolic execution, fault localization, model checking, security and performance. The course combines theory with practical implementation and usage. Prerequisites: CS 3240.

A graduate student returning from Curricular Practical Training can use this course to claim one credit hour of academic credit after successfully reporting, orally and in writing, a summary of the CPT experience to his/her academic advisor.

Detailed study of graduate course material on an independent basis under the guidance of a faculty member.

Detailed study of graduate course material on an independent basis under the guidance of a faculty member.

Formal record of student commitment to project research for the Master of Computer Science degree under the guidance of a faculty advisor.

For master's students who are teaching assistants.

Formal record of student commitment to thesis research for the Master of Science degree under the guidance of a faculty advisor. May be repeated as necessary.

For doctoral students who are teaching assistants.