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