Appendices
References
MIT Parallel Computing and Scientific Machine Learning
Download PDF
Download ePub
Preface
Introduction to Parallel Computing
1
Optimizing Serial Code
2
Introduction to Scientific Machine Learning through Physics-Informed Neural Networks
Parallel Computing
3
How Loops Work, An Introduction to Discrete Dynamics
4
The Basics of Single Node Parallel Computing
5
The Different Flavors of Parallelism
6
Ordinary Differential Equations, Applications and Discretizations
Modern Approaches
7
Forward-Mode Automatic Differentiation (AD) via High Dimensional Algebras
8
Solving Stiff Ordinary Differential Equations
9
Basic Parameter Estimation, Reverse-Mode AD, and Inverse Problems
10
Differentiable Programming and Neural Differential Equations
Modern Architectures
11
Introduction to MPI.jl
12
GPU programming
Advanced Differential Equations
13
PDEs, Convolutions, and the Mathematics of Locality
14
Mixing Differential Equations and Neural Networks for Physics-Informed Learning
15
From Optimization to Probabilistic Programming
16
Global Sensitivity Analysis
Advanced Topics
17
Code Profiling and Optimization
18
Uncertainty Programming, Generalized Uncertainty Quantification
Appendices
References
References
18
Uncertainty Programming, Generalized Uncertainty Quantification