Networks Design Projects

COMPSCI 2440R Subject & Catalog Number

Description

The contents and course requirements of CS 244R are similar to those of CS 1440R, with the exception that students enrolled in CS 2440R are expected to do substantial system implementation and conduct rigorous performance analysis for their design projects, and perform graduate-level work to earn the same letter grade.

In this course, students will learn how to utilize tools powered by large language models (LLMs) to address real-world design challenges, including the generation of code and circuits. This field represents the forefront of technology and is rapidly evolving, with new insights and lessons emerging frequently. For example, recent advancements in reasoning models have significantly improved the success rate of producing designs that are not only correct but also efficient. As a result, there is a growing emphasis on the computational efficiency of inference, which enhances deeper reasoning capabilities. Related research includes developing methods for automatically generating testbenches to evaluate and validate designs created by LLMs.

A student's work includes the following activities: (1) reviewing articles about various experiments that explore the use of LLM tools in design, (2) creating presentations based on these articles and delivering them in class, and (3) collaborating in teams of 2 or 3 on a design project that utilizes LLM-assisted tools, applying the knowledge gained from the literature.

Course Notes

Preference will be given to upper-class undergraduates or graduate students majoring in Computer Science or Electrical Engineering. Please note that this course was previously listed as CS 244R.