ELEC 515 Embedded Machine Learning - General Information


need photo here 

Yingyan Lin
Assistant Professor
Electrical and Computer Engineering
Rice University

Office: Duncan Hall 2040
Tel: 713-348-3020

Time and Location


Mon. 9:40AM - 10:55AM
Wed. 9:30AM - 10:45AM
(26-AUG-2019 - 6-DEC-2019)


DCH 1075

Course Description

Machine learning is in tremendous demand in numerous applications; however, its often prohibitive complexity remains a major challenge for its extensive deployment in resource constrained platforms. This course will introduce techniques for developing energy/time efficient machine learning systems. In particular, you will first learn commonly used machine learning algorithms, and then state-of-the-art techniques for reducing the energy/time cost of machine learning systems while maintaining their powerful performance. Finally, we will do a deep dive into state-of-the-art efficient machine learning systems, such as Google's TPU and Eyeriss.


Topics are self-contained so that a background in machine learning is not required. Students should be familiar with programming to complete their course projects.

Learning Outcomes

By the end of the semester, students will:

  1. Understand commonly used ML algorithms;

  2. Understand challenges of embedded ML techniques;

  3. State-of-the-art embedded ML techniques;

  4. Know how to use commonly employed tools to evaluate/validate embedded ML ideas:

    1. analytical models;

    2. ASIC synthesis;

    3. FPGA synthesis;

    4. mobiles (TensorFlow Lite);

Grading Policy

  1. Lecture: 1 (15%)

  2. Paper presentation: 2 (15%)

  3. Homework: 1 with 3 milestone updates (25%)

  4. Course project: 1 with 4 milestone updates (35%)

  5. participation(10%)


Lecture notes and assigned technical papers.

Collaboration Policy and the Rice Honor Code

All students should uphold the standards of the Rice Honor Code, which you pledged to honor when you matriculated/enrolled at this institution. For details, please refer to the the Honor System Handbook at http://honor.rice.edu/honor-system-handbook, which outlines the University’s expectations for the integrity of your academic work, the procedures for resolving alleged violations of those expectations, and the rights and responsibilities of students and faculty members throughout the process.

Discussion and collaboration are encouraged. However, all your hand-in assignments and presentations should reflect your own understanding of the topic. Also, you may consult any papers, books, online references, or publicly available implementations of open-source code and incorporate them into your homework assignment, presentation or course project. Keep in mind, however, you have to clearly cite your sources in your presentation or write-up.

Disability Support Services

If you have a documented disability needing academic adjustment or accommodation, please speak with me about  your needs during the first two weeks of the class. All discussions will remain confidential. Also, please make sure that you are on file with Disability Support Services (Allen Center, Room 111)