Physics-aware machine learning and data assimilation
  • Luca Magri
  • People
    • Group
    • Collaborations
  • Publications
  • Research
    • Overview
    • Data assimilation and UQ
    • Physics-aware machine learning
    • Optimization
    • Chaos
    • Reacting flows
    • Sound
    • Linear methods from quantum mechanics
  • Teaching
    • University modules
    • Artificial intelligence for engineering
    • Mathematical methods
    • Summer/winter schools
  • Misc
    • Contact
    • Opportunities
    • Outreach >
      • Data-driven methods, machine learning and optimization
      • Data-driven Dynamical Systems Analysis
    • DNS Database
    • Open-source software

Artificial intelligence for engineering

Lecture notes (handouts, codes and Jupyter notebookes)

1. Introduction to machine learning, data science, artificial intelligence. What are they? Why in engineering?
2. Linear regression
3. Logistic regression (classification)
4. Support vector machines
5. Feedforward neural networks
6. Convolutional neural networks
7. Recurrent neural networks and sequence modelling
8. Unsupervised learning 

Download: Syllabus

Handouts, Jupyter codes, and slides are available on BlackBoard (restrict access)

Videos

Computational graphs and feedforward neural networks 


Forward propagation and backpropagation
Convolutional neural networks
Unsupervised learning
© 2023 Luca Magri
  • Luca Magri
  • People
    • Group
    • Collaborations
  • Publications
  • Research
    • Overview
    • Data assimilation and UQ
    • Physics-aware machine learning
    • Optimization
    • Chaos
    • Reacting flows
    • Sound
    • Linear methods from quantum mechanics
  • Teaching
    • University modules
    • Artificial intelligence for engineering
    • Mathematical methods
    • Summer/winter schools
  • Misc
    • Contact
    • Opportunities
    • Outreach >
      • Data-driven methods, machine learning and optimization
      • Data-driven Dynamical Systems Analysis
    • DNS Database
    • Open-source software