jaamestaay / M2R-Group-29

This repository complements the MATH50002 (M2R) research report and presentation, a compulsory year two Mathematics module at Imperial College London. We introduced and explored neural networks and the techniques required to train a neural network. We then discussed neural ODEs and their increased accuracy, before extending to neural CDEs.
0 stars 0 forks source link

Scientific Machine Learning: Neural Networks and Neural Differential Equations

This is the GitHub repository for the MATH50002 Group Research Project (M2R) by Group 29.

You can find all relevant codes, figures, and LaTeX files here.

Group Members:

Group Supervisor:

The outline of our report (along with the relevant contributors) is detailed below.

1. Introduction (Jiaru, James)

2. Neural Networks

2.1 History (Jiaru)

2.2 Concepts

2.3 Optimisation Techniques (James)

2.4 Example: Regression (Jiaru)

2.5 Example: Classification (Jiaru)

3. Neural ODEs

3.1 Motivation (Xinyan)

3.2 Comparing Neural ODEs with ResNet (Xinyan)

3.3 Various Neural ODE Models (Xinyan)

3.4 Solving ODEs Numerically (James)

3.5 Backpropagation in Neural ODEs (James, Xinyan)

3.6 Adjoint Sensitivity Method (Xinyan)

4. Application: Digit Classifier with Neural ODEs

4.1 Implementation (Jiankuan, Jiaru)

4.2 Comparison (Jiankuan, Xinyan)

5. Extension: Neural CDEs (Tianshi)

5.1 Motivation

5.2 Controlled Differential Equations

5.3 Neural CDEs

5.4 Solving Neural CDEs

5.5 Application: Time Series Modelling

6. Conclusion (James)

Acknowledgements (James)

References

Appendices

A Proof of Convergence of Gradient Descent Algorithm (James)

B Comparison of ODE Solvers (James)

C A Simple Example of the Adjoint Method (Xinyan)

D Data Preprocessing of Financial Time Series (Tianshi)