Problems
Machine Learning for Mechanical Engineering
Preface
1
Introduction
Foundational Skills
2
Reviewing Supervised Linear Models
3
Evaluating Machine Learning Models
4
Introduction to Gradient Descent
5
Review of Linear Unsupervised Learning
6
Taking Derivatives with Automatic Differentiation
7
Measuring Distribution Distances
8
Introduction to Inference
9
Introduction to Probabilistic Programming
Foundations of Generative Models
10
Review of Neural Networks
11
Introduction to Push-Forward Generative Models – Generative Adversarial Networks (GANs)
12
GAN Training Pitfalls
13
Optimal Transport for Generative Models
14
Variational Autoencoders (VAEs)
15
Normalizing Flows
16
From Discrete Transformations to Continuous Flows
17
From Continuous Flows to Score Matching
18
From Score Matching to Diffusion Models
19
Flow Matching
20
Latent Generative Models
21
Introduction to Deep Reinforcement Learning
22
Introduction to Transformers
Engineering-Specific Considerations
23
Active and Semi-Supervised Learning
References
Problems
24
Problem Set 1
25
Problem Set 2
In-Class Notebooks
26
Housing Price Data Visualization In-Class Exercise
Appendices
A
Helpful Tooling for Working with and Debugging Machine Learning Models
B
Review of Matrices and the Singular Value Decomposition
C
Reviewing Mathematical and Computational Foundations for Machine Learning
Problems
Here are the problem sets
References
24
Problem Set 1