Syllabus

Welcome to this Training Workshop on the application of ML to natural hazards engineering. This year’s offering will be in an online format. A drawback of an online offering is the lack of interaction among the participants, so we encourage you to be active during the live sessions with questions.

Note

The training for days 3 through 5 is organized as a series of pre-recorded video lectures and live online conferencing (Zoom). The lessons and videos for these days are provided in the expanded syllabus for these days given below.

Day 1: ML in Earthquake Engineering: Opportunities and Challenges

  • In-class presentations

    • Introduction: Slides

    • Machine Learning in Infrastructure Risk and Resilience Assessment - A Constructive Critique: Slides

Day 2: Explainable AI in Earthquake Engineering

Day 3: Image Classification

  • Pre-class content

    • Multi-Layer Perceptron: Video

    • Convolutional Neural Networks: Video

    • Attention Networks: Video

    • Transformers: Video

  • In-class presentation

    • Image Classification: Slides

  • Demo

Day 4: Semantic Segmentation

  • Pre-class content

    • An Overview of Image Segmentation Algorithms: Video

    • State of the Art Image Segmentation Algorithms, Segmentation Datasets: Video

  • Demos

Day 5: Inventory Generation with BRAILS

  • In-class content

    • Introduction to BRAILS’ Inventory Generation Capabilities: Slides

  • Demo

Warning

  1. Videos must be watched before the online class sessions for days 3 and 4. On days 3 and 4, we will spend our live sessions mostly doing hands-on demos, questions, and discussion. These demos are only effective if you do your self-study assignment of watching the videos before we meet.

  2. To run the demo on Day 5, you need to get a Google Maps API key before the class. Follow the instructions: “Using API Keys” in this link.