MTH786P - Machine Learning with Python - 2023/24
| Topic | Name | Description |
|---|---|---|
These are the lecture notes originally developed for this module by Dr. Benning. |
||
Passcode: hT.&cv9x Passcode: 45Gz8@9n Tutorial 3 Unfortunately missing due to a broken microphone Passcode: eX6J$d.6 Passcode: &8Huf.d4 Tutorial 6 (mainly conducted on the whiteboard in preparation of the mid-term) Passcode: 7uF+u=q4 Passcode: @9Vs9jEE Passcode: r90p!8c5 Passcode: 6r&=1sEY Passcode: 4SgE#45f Passcode: ?N!3byA7 |
||
| Week 0: Coursework 0 | ||
| Week 1: Introduction. Mathematical preliminaries. | ||
| Week 2: Linear regression. Polynomial regression. | ||
| Week 3: Ill-conditioned regression problems | ||
| Week 4: Empirical risk minimisation & model error structure. | ||
| Week 5: The LASSO and the gradient descent. | ||
| Week 6: Regression analysis with Neural Networks. | ||
| Week 7: Midterm assessment. | ||
| Week 8: Classification problems. Non-parametric classification. | ||
| Week 9: Logistic regression | ||
| Week 10: Support Vector Machines | ||
| Week 11: Semi-supervised binary classification with graphs | ||
| Hints and tips | Note that this online tutorial is also available as Jupyter notebook, see https://github.com/kuleshov/cs228-material/blob/master/tutorials/python/cs228-python-tutorial.ipynb. |
|
We use the Anaconda distribution to run Python 3, as it is easy to install and comes with most packages we need. To install Anaconda, go to the linked url and get the Python installer for your OS - make sure to use the newer version 3.x, not 2.x. Follow the instructions of the installer and you're done. Warning! The installer will ask you if you want to add Anaconda to your path. Your default answer should be yes, unless you have specific reasons not to want this. |
||
This is a link to the Numpy Quickstart tutorial from SciPy.org. |
||
| coursework | ||
| exam papers | ||
| Week 12: Decision Trees | ||
| Final Project (Deadline: 24/01/24) | This file details the requirements of the project. Please read it with great attention |
|
Five datasets to pick from. You need to pick one |
||
| Mathematics for Machine Learning (freely available textbook) | This textbook might be a good resource especially for the more theoretical aspects of the course (i.e., linear algebra, calculus, etc..) |
