Course Schedule and Catalog

Department: Electrical & Computer Eng.

Meeting: 2:30PM - 3:45PM TR (11-JAN-2027 - 23-APR-2027) 

Part of Term: Full Term

Grade Mode: Standard Letter

Course Type: Lecture

Language of Instruction: Taught in English

Method of Instruction: Face to Face

Credit Hours: 3

 

Prerequisites: COMP 140 AND (ELEC 242 OR COMP 182) AND (ELEC 326 OR COMP 326)

Section Max Enrollment: 40

Section Enrolled: 0

Enrollment data as of: 2-NOV-2026 5:04AM

 

 

Final Exam: Scheduled Final Exam-OTR Room

 

Description: Modern machine learning is built from recurring computational patterns, including dense matrix operations, streaming and transform computation, similarity search, iterative optimization, and sparse or irregular processing. Performance depends not only on an algorithm’s mathematical formulation, but also on how effectively its parallelism, dataflow, and memory behavior map onto hardware. This course examines machine learning from a computer architecture and systems perspective. Students learn to identify computational bottlenecks and study efficient implementations of representative machine-learning and signal-processing methods across CPUs, GPUs, FPGAs, ASICs, and specialized accelerators. The course then applies these principles to modern AI inference, including neural networks, transformers, large language models, diffusion models, and emerging computing architectures. Hands-on projects provide experience implementing, profiling, and comparing workloads across hardware platforms. Recommended Prerequisite(s): ELEC 378