Course Syllabus

ML using GoogleCloud AutoML and MATLAB

 
Apply Here
  • Course Information
  • Fee: Free
  • Lenght: 2 Sessions, 3 hours each on 2 days
  • Location: SDSU HealthLINK Center

Download PDF for Directions

Dates:

  • September 14, 2026
  • 1:00 PM - 4:00 PM
  • September 21, 2026
  • 1:00 PM - 4:00 PM
  • # of Students: 20
  • Mode of Delivery: In Person

Prerequisites:

  • Basic computer knowledge
  • Basic statistics background
  • Instructor Information​

Dr. Kee Moon is a professor in the Department of Mechanical Engineering at SDSU and a Co-Leader of the Research Capacity Core & Health Sensor Methods Group at the SDSU HealthLINK Center. Dr. Kee Moon’s primary research interests are in smart sensor and actuator technology, including the development of ultrasonic recharging technology for implantable medical devices as well as brain-computer-interface technology. At the SDSU HealthLINK Center, Dr. Kee Moon guides researchers on the development of portable, wearable health sensor technologies that can provide real-time health monitoring.
Preferred title: Dr. Moon

  • Key Learning Objectives

By the end of this course participants will be able to:

  • Describe common machine learning techniques
  • Understand the toolbox of available options in MATLAB for machine learning
  • Describe considerations regarding how to interpret and evaluate machine learning models
  • Apply cloud-based machine learning techniques using AutoML
  • Course Outline

This two-day (6-hour) workshop introduces machine learning fundamentals using Gemini Enterprise Agent Platform (AutoML) and MATLAB Machine Learning Toolbox. Topics include supervised and unsupervised learning, data preparation, model training, validation, and evaluation. Participants will develop machine learning models through hands-on exercises and apply them to wearable health sensor data in a real-world case study.

Session 0

Pre-reqs, verification

Session 1 (3 hours, day 1)

Introduction to Machine Learning & Google Cloud AutoML

Session Overview

This session introduces the fundamental concepts of machine learning and provides hands-on experience using Gemini Enterprise Agent Platform (AutoML) to build supervised machine learning models without programming. Participants will learn the complete workflow from organizing datasets to training, evaluating, and deploying a classification model using Google’s cloud-based AutoML platform.

Topics Covered

Machine Learning Fundamentals
  • Machine Learning Types
    • Supervised Learning
    • Unsupervised Learning
    • Reinforcement Learning
Google Cloud Vertex AI
  • AutoML Workflow
  • Google Cloud Project Setup
  • Cloud Storage
  • AutoML Classification
  • Model Evaluation
  • Model Deployment
Software
  • Google Cloud Platform
  • Google Gemini Enterprise Agent Platform (AutoML)
  • Google Chrome

Hands-On Exercise 1

Penguin Species Classification Using Google Cloud Vertex AI (AutoML)

Participants will build a complete supervised machine learning model by:

  • Preparing the dataset
  • Uploading data to Google Cloud
  • Training an AutoML classifier
  • Evaluating classification performance
  • Deploying and testing the model

Session 2 (3 hours, day 2)

Machine Learning Using MATLAB

 Session Overview

This session introduces participants to MATLAB Machine Learning Toolbox and demonstrates how to develop machine learning models using MATLAB’s interactive apps. Participants will learn how to build, train, validate, and evaluate supervised and unsupervised learning models through hands-on exercises and conclude with a real-world case study using Q-Life wearable EMG/IMU sensor data.

Topics Covered

MATLAB Machine Learning Toolbox

  • Machine Learning Toolbox Overview
  • Classification Learner App
  • Regression Learner App
  • Model Comparison Tools

Supervised Learning

  • Classification
  • Regression
  • Feature Selection
  • Model Validation
  • Cross-Validation
  • Performance Metrics

Unsupervised Learning

  • Clustering Concepts
  • K-Means Clustering
  • Cluster Visualization

Hands-On Exercise 2

  • Developing Classification Models in MATLAB
  • Predicting Human Activity Types

Case Study

  • Training Models with Q-Life Wearable Sensor Data
  • Convolutional Neural Network (CNN) Basics

Software

  • MATLAB®
  • Machine Learning Toolbox™
    • Statistics and Machine Learning Toolbox
    • Deep Learning Toolbox

Hands-On Exercise 2

Developing Machine Learning Models in MATLAB

This session provides participants with practical experience using MATLAB’s machine learning tools and demonstrates how AI can be applied to real-world biomedical sensor data for digital health applications.

Key Learning Objectives

By the end of this session, participants will be able to:

  • Understand the fundamental concepts of machine learning.
  • Differentiate between supervised, unsupervised, and reinforcement learning.
  • Recognize common healthcare and biomedical applications of machine learning.
  • Prepare datasets for machine learning model development.
  • Create and configure a Google Cloud project for AutoML.
  • Train, evaluate, and deploy a supervised classification model using AutoML.
  • Apply AutoML to a real-world biological classification problem.
  • Navigate the MATLAB Machine Learning APP.
  • Use the Classification Learner App to develop machine learning models.
  • Build and evaluate classification models using Classification Learner App.
  • Apply clustering techniques for exploratory data analysis.
  • Course Materials

Reading requirements

To be provided by Dr. Moon

Dataset

To be provided by Dr. Moon, Will be downloaded on day of class