ÌÇÐÄTV

General Information

Check this website for future updates. We will also be using the mailing list to contact you; make sure you are registered for the module. If you have any questions, please contact (both) the module organisers:

• Amina Asif - Amina.Asif@warwick.ac.uk 
• Gabriele Pergola - Gabriele.Pergola.1@warwick.ac.uk 
  
  

Timetable

• Lectures
  • Monday at 1pm–2pm in
  • Tuesday at 9am–10am in (Junction)
  • Wednesday at 12pm–1pm in (Junction)
• Labs
  • Thursday at 9am–10am in
  • Thursday at 3pm–4pm in

    Please attend the workshop group to which you have been allocated on Tabula.

Details of the timetable can be found hereLink opens in a new window.

Labs

In order to attend a lab session, you need to have registered for the module. Attendance at lab sessions is obligatory and their purpose is to help you with assessed assignments and provide oral feedback.

Labs and TA contact details

Teaching Assistants:

• Boyang Fu: Boyang.Fu@warwick.ac.uk 
• Piotr Keller: Piotr.keller@warwick.ac.uk

On-campus labs:

• Thursday 9–10am: CS0.01
• Thursday 3–4pm: MB3.17
  
  

Assignments

There are two assignments, each worth 25% of the final mark. The other 50% will be from the final exam in May/June.

Assignment 1 — 25%

• Release: Week 2
• Deadline: Week 6, Thursday, 12 November 2026, 12 noon

Material:

• • Coursework Brief 
  • Dataset

Assignment 2 — 25%

• Release: Week 6
• Deadline: Thursday, Week 11
• Submission via Tabula link [TBC]

Note that any submission after the deadline will incur a penalty of 5% per day. No submission will be accepted beyond 6 days after its corresponding deadline.

If the wrong file is submitted and the deadline has passed, please contact dcs.ug.support@warwick.ac.ukLink opens in a new window to have the original submission removed so that you are able to upload a new submission. This will incur a late penalty. Late penalties will not be waived unless via a Mitigating Circumstances panel decision.

Lab Access and Machine Requirements

Use "module load cs909-python". The following guide will show you how to run Jupyter-notebook as well as loading using notebooks with the module loaded in Visual Studio Code:

• Notebook and VSCode Setup GuideLink opens in a new window

If using your own machine, you will be needing the listed libraries:

• Anaconda Python (3.6+), Jupyter Notebook or Jupyter Lab, Matplotlib, Numpy, SciPy, Pandas, Scikit-learn, Keras, PyTorch, TensorFlow (with GPU configuration, if GPUs available).

If needed, Remote Machine Login: /fac/sci/dcs/intranet/user_guide/remote-login/

Resources

Textbooks

The module does not follow strictly a single textbook. The following books provide useful complementary references:

• G. James, D. Witten, T. Hastie, R. Tibshirani (2023). . Shorter and simpler version of the next one.
• T. Hastie, R. Tibshirani, J. Friedman (2017). .
• Murphy, K. P. (2022). Probabilistic Machine Learning: An Introduction.

• Deisenroth, M. P., et al. (2020). .

• Goodfellow, I., Bengio, Y., & Courville, A. (2016). .
• Nielsen, M. A. (2015). .

Python books

If you don't have any experience with Python, or want to learn more about programming with Python, the following books are useful:

• , by Pieter Spronck
  
  

Module Schedule

Lecture recordings are available via .

Week	Lectures	Reading	Seminars	Labs
1	1. Introduction to Machine Learning 2. Classification, Feature Spaces and Linear Discriminants 3. Optimisation and the Perceptron	-	-	Assignment 1
2	4. From the Perceptron to the Support Vector Classifier 5. Kernels and SVMs	-	Continual Learning. J. Hurtado [Slides] [Notebook]	Assignment 1
3	6. Decision Trees 7. Evaluating and Comparing Models: Binary Classification	-	From Pixels to Patient Outcome: ML Research in Computational Pathology. N. Wahab.	Assignment 1
4	Multivariate Analysis & Dimensionality Reduction
5	Regression & Unified Frameworks
6	Deep Learning
7	-
8	-
9	-
10	-
	-