Academics / Courses / DescriptionsIEMS 352: Foundations of Generative AI & Reasoning Systems
VIEW ALL COURSE TIMES AND SESSIONS
Description
Generative AI is transforming how we learn, create, and build AI models and software—and this course provides a hands-on introduction to the science and algorithms behind today’s Large Language Models (LLMs). You’ll learn how transformer-based models are architectured, trained and deployed, then venture into the techniques that power real-world genAI applications: prompt engineering (including algorithmic approaches), and post-training with reinforcement learning methods such as RLHF and direct preference optimization (DPO). The course also covers large reasoning models, in-context learning, and efficient adaptation via fine-tuning (LoRA), with a look at emerging foundation models beyond text (e.g., time-series). The course assignments require use of code assistants to develop imlementations for a variety of use cases and topics. Practical implementations by using modern software techniques and understanding of the science of LLMs are two main goals of the course.
Knowledge of predictive analytics at the level of IEMS 304 is required, in particular, classification algorithms
such as naïve Bayes, SVM, logistic regression, and random forests.
- This course will NOT teach about
- Classification algorithms
- Big data (too complex and messy)
- Fundamentals of Python (students are expected to know or learn by themselves the basics of Python)