Machine Learning for Engineers

This course is designed to immerse engineering students in the world of machine learning.

Machine learning drives technological advancement by leveraging data to gain experience. It represents a fusion of linear algebra, statistics, optimization, and computational techniques, enabling computer systems to infer relationships and make decisions from data.

This course, "Machine Learning for Engineers", is designed to immerse engineering students in the world of machine learning. It offers a comprehensive overview of both theoretical concepts and practical applications of machine learning in engineering. The course content is tailored to provide an intuitive understanding of machine learning, covering a range of topics from unsupervised to supervised learning methods.

Professor

John Hedengren leads the BYU PRISM group with interests in combining data science, optimization, and automation with current projects in hybrid nuclear energy system design and unmanned aerial vehicle photogrammetry. He earned a doctoral degree at the University of Texas at Austin and worked 5 years with ExxonMobil Chemical prior to joining BYU in 2011.

Course Overview

Key aspects of the course include:

• Practical Applications: Students explore how machine learning is reshaping various industries with a focus on engineering applications.
• Case Studies: The course includes several case studies, providing students with practical insights into classification and regression methods.
• Hands-on Experience: A significant portion of the course is dedicated to a hands-on group project, allowing students to apply their learning to real-world engineering problems.
• Tools and Techniques: The course emphasizes the use of MATLAB and Python, equipping students with the skills to implement state-of-the-art machine learning methods.

Data Engineering

• Overview
• 1️⃣ Gather Data
• 2️⃣ Statistics
• 3️⃣ Visualize
• 4️⃣ Cleanse
• 5️⃣ Features
• 6️⃣ Balance
• 7️⃣ Scale
• 8️⃣ Split
• 9️⃣ Deploy

Classification

• Overview
• Hyperparameters
• Cybersecurity

Supervised Learning

• AdaBoost
• Decision Tree
• k-Nearest Neighbors
• Logistic Regression
• Naïve Bayes
• Neural Network Classifier
• Random Forest
• Stochastic Gradient Descent
• Support Vector Classifier
• XGBoost Classifier

Unsupervised Learning

• Gaussian Mixture Model
• K-Means Clustering
• Spectral Clustering

Regression

• Overview
• Linear Regression
• k-Nearest Neighbors Regression
• Support Vector Regressor
• Gaussian Processes
• Neural Network Regressor
• XGBoost Regressor

Time-Series

• ARX Model
• LSTM Network

Computer Vision

• Introduction
• Cascade Classifier
• Deep Learning

Applications

• Additive Manufacturing 📈📊
• Automation with LSTM ⏱️
• Automotive Monitoring 📈📊
• Bit Classification 👁️📊
• Concrete Strength 📈📊
• Draw Classification 📊
• Facial Recognition 👁️📊
• Hand Tracking 👁️
• IOT/OT Cybersecurity ⏱️📊
• Lithium-ion Batteries 📊
• Polymer Regression 📈
• Road Detection 👁️📊
• Soil Classification 👁️📊
• Sonar Detection 📊
• Steel Plate Defects 📊
• Texture Classification 👁️📊
• Thermophysical Properties 📈
• Wind Power ⏱️📈

📈=Regression

📊=Classification

⏱️=Time Series

👁️=Computer Vision

🎧=Audio

MATLAB and Python Repositories on Github

Course Web-site and Schedule

The materials in this archive are released under the MIT License. The financial assistance of MathWorks is gratefully acknowledged with technical assistance of Aycan Hacioglu, Jonathon Loftin, Jianghao Wang, Jacob Burrell, Krystian Perez, Sean Last, Spencer Larson, Sion Jung, Andrew Crop, Andrew Fry, Nathan Phillips, and Hannah Hanson.

For more details on the course content and structure, visit Machine Learning for Engineers course page.