Skip Navigation

Introduction to Embedded AI

Course closed to new registrations: Call ( 949 ) 824-5414 for more information or sign up below to be notified when this course becomes available.×

Course Description

Artificial intelligence (AI) is being incorporated into small, low-power embedded computing devices for consumer electronics, industry, and the Internet of Things (IoT). Learn about embedded AI and the technological developments and other factors that are motivating new and exciting embedded AI applications. Explore the devices, signal processing methods, embedded machine learning (ML) algorithms, and embedded ML frameworks that are used to create embedded AI systems. Explore embedded AI use cases such as object recognition, wake word detection, and gesture recognition. Use hands-on examples and activities to explore embedded AI applications that use ML models for on-device processing of audio, motion, and many other signals. Understand the unique challenges posed by the deployment of ML models on resource-constrained devices in TinyML applications. For AI applications in IoT (AIoT), review the benefits of edge computing and the tradeoffs considered when making decisions about whether AI processing is done on the edge device or in the cloud.

Note students are required to purchase the following

Arduino Nano 33 BLE Sense with headers (Arduino Nano 33 BLE Sense without headers is acceptable). Some possible options for purchase (you may wish to purchase early - semiconductor supply chain issues may impact availability)

Connecting the board requires a micro USB cable (which you may already have on hand)

Recommended Prerequisite: Basic knowledge of C programming.

  • Be notified when this class becomes available!

  • Details
  • $745
  • January 10, 2022 to March 20, 2022
  • Delivery Mode: Online
  • Reg#: 00122
  • ID/Units: EECS X480.1  (3.00)
    ( Section 1 )
  • Quarter: WINTER 2022

Instructor


Thomas C. Jannett, M.S., Ph.D., is Professor Emeritus of Electrical and Computer Engineering at The University of Alabama at Birmingham. He has more than 30 years of experience in teaching and research. Research expertise includes smart sensor networks that use intelligent control and signal processing. He developed instruments and rehabilitation devices that use embedded microcomputers for data acquisition, signal processing, and intelligent control. He has published extensively in these areas. Current interests include analytics, machine learning, and the Internet of Things.

Textbook Information

Textbooks for your course may be purchased from any vendor or bookseller of your choice.

Required Textbook(s):

LEARNING DEEP LEARNING: THEORY AND PRACTICE OF NEURAL NETWORKS
Book - ISBN: 9780137470358
Magnus Ekman, 1 ed, Addison-Wesley Professional

TINYML: MACHINE LEARNING WITH TENSORFLOW LITE ON ARDUINO
Book - ISBN: 9781492052043
Pete Warden, Daniel Situnayake, 1 ed, O'Reilly

Meeting Schedule

EventDateDayStart TimeEnd TimeLocationRoom
START01/10/2022Monday------Online (Access Begins)---
END03/20/2022Sunday------Online (Access Ends)---