Special Topics

Undergraduate Courses

Winter 2024

EEC189L: Quantum Computing

• CRN: 22425 and 22426, Units: 4
• Professor Marina Radulaski
• Date/Time: M 2:10 - 3:30 PM & 6:10 - 8:00 PM, W 2:10 - 3:30 PM
• Prerequisites: MAT 22A (may be concurrent), ENG 06, or another programming course
• Course Description: Learn the principles of and get hands-on experience with quantum computing! This course is aimed at sophomore and junior students with interest in quantum computing who are familiar with the basics of linear algebra such as vector spaces and matrix manipulations. The course learning goals aim for students to:
  • Understand how quantum information is represented and how it differs from classical information,
  • Become familiar with the unintuitive concepts of quantum mechanics such as the superposition and entanglement,
  • Become familiar with the physical implementations of quantum hardware,
  • Learn to design a quantum circuit,
  • Learn to program in Qiskit open-source quantum computing software development framework,
  • Learn basics of quantum algorithms,
  • Apply physical concepts to quantum information hands-on demos,
  • Develop interdisciplinary communication and presentation skills.

Graduate EEC 289 Courses

Fall 2024

EEC 289Q: Practical AI

• CRN: 30220, Units: 4
• Professor Houman Homayoun
• Lecture – 4 hours/week
• Graduate Student Status
• Course Description: The recent advancements in artificial intelligence (AI) have significantly impacted a wide range of applications, from natural language processing and computer vision to autonomous systems and smart environments. This course provides a comprehensive introduction to practical AI, focusing on the application of AI techniques in real-world scenarios. It aims to equip students with the knowledge to apply AI techniques effectively and understand the current state-of-the-art methods in AI, including large language models (LLMs) and natural language processing (NLP). The course is designed for students and practitioners familiar with application requirements, helping them select and apply appropriate AI techniques to solve specific problems.  
• Through the course, the students will gain a deeper understanding of both classic and recent techniques used in discrete optimization, and will grow into informed users of optimization tools and methodologies that may find application in their research area. The material will be motivated and discussed in the context of a large number of example problems that arise in different subareas of computer engineering, such as electronic design automation, compilers and operating systems.

EEC 289Q: Deep Learning Hardware

• CRN: 50201, Units: 4
• Professor Avesta Sasan
• Lecture – 4 hours/week
• Pre-Requisites: EEC196 {can be concurrent}; and Consent of Instructor
• Course Description: This course is designed to equip students with a comprehensive understanding of the hardware aspects of machine learning. The lecture-style course will cover fundamental concepts in deep learning, hardware accelerators, hardware co-optimization, and techniques for improving hardware efficiency when executing inference on deep learning networks. Students will also assigned and conduct individual research on a given topic related to hardware for machine learning, which they will present in the form of a survey and a 20-minute lecture. By the end of the semester, students will be expected to present their research findings to the class.      

Winter 2025

EEC 289S: Digital Health Instrumentation

• CRN: TBD , Units: 4
• Professor Hyoyoung Jeong
• Lecture - TBD
• Pre-Requisites: Working knowledge of analog and digital circuits, as well as signal processing, or permission of the instructor.
• Course Description: The course is divided into two halves: the first half focuses on building fundamental knowledge and technical skills in medical instrumentation, including topics such as analog sensors, operational amplifiers, noise filters, and physiological measurement principles. The second half focuses on complementary factors, such as advanced design considerations, noise control, power management, gold-standard patient monitoring, and project implementation.

Spring 2025

EEC 289A: Introduction to Unsupervised Learning

• CRN: TBD, Units: 4
• Professor Yubei Chen
• Lecture - TBD
• Prerequisites: ECS 171, or ECS 174, or EEC 174AY, or equivalent; All students need to know python programming. (or instructor consent)
• Recommended: Proficiency in linear algebra, calculus or mathematical analysis, applied probability, optimization, and deep learning.
• Course Description: Humans and other animals exhibit learning abilities and understanding of the world that are far beyond the capabilities of current AI and machine learning systems. Such capabilities are largely driven by intrinsic objectives without external supervision. Unsupervised learning (also known as self-supervised learning) aims to build models that find patterns in data automatically and reveal the patterns underlying data explicitly with a representation. In the past few years, this subject has not only become one of the pillars for modern machine learning systems, but also provides insights for modeling biological sensory systems. This course covers the historical trajectory (e.g., clustering, spectral embedding, mixture models) and frontier development of unsupervised learning (like deep energy-based models, score-matching based models or diffusion models, and joint-embedding self-supervised learning). The goal is to build the theoretical foundations for the students and help them catch the frontier of this field. Further, students will be required to review selected papers and form groups to present several frontier research topics as mini lectures. Students will also form into groups to work on a final project. This introduction to unsupervised learning will help students significantly improve their ability to conduct fundamental machine learning research or apply the advanced machine learning techniques in their future work.