Alessandro De Palma

This course is available on the CEMS Exchange, MPA in Data Science for Public Policy, MSc in Applied Social Data Science, MSc in Data Science, MSc in Financial Statistics, MSc in Financial Statistics (Research), MSc in Geographic Data Science, MSc in Health Data Science, MSc in Management of Information Systems and Digital Innovation, MSc in Mathematics and Computation, MSc in Operations Research & Analytics, MSc in Quantitative Methods for Risk Management, MSc in Statistics and MSc in Statistics (Research). This course is available with permission as an outside option to students on other programmes where regulations permit. This course uses controlled access as part of the course selection process. For information on controlled access courses, including eligibility, application processes, deadlines, and departmental contact details, please refer to the Controlled Access Courses webpage.

How to apply: Please be advised that spaces on this course will be extremely limited, so early application is advisable. Priority will be given to students on the MSc Data Science.

Students from any other programmes should submit a short statement indicating a) why they think the course is suitable for them given their background knowledge and b) their motivation for their choice.

Deadline for application: Due to the nature of the method of application, interested students should apply as soon as possible after the opening selection and no later than 9:30am on Thursday 24 September 2026.

Course lecturers will aim to make initial offers to students on LSE For You by Thursday 24 September.

For queries contact: Stats-Msc@lse.ac.uk.

MSc Data Science students will be given priority for enrollment in this course.

The course requires knowledge of basic concepts in linear algebra, calculus and probability. A basic knowledge of computer programming (Python) is expected. A quantitative background (e.g, a degree in Statistics, Computer Science, Mathematics, Engineering or related areas) would be recommended.

This course covers fundamental concepts within deep learning including: neural networks, training and evaluation methods, specialised network architectures designed for both predictive and generative tasks on various data domains (images, sequences, natural language processing), and large language models.
Specifically, the course will cover the following topics:

1. Introduction to neural networks: single-layer networks, (multi-layer) perceptrons and feedforward neural network architecture.
2. Neural network training: empirical loss function minimisation, (stochastic) gradient descent, backpropagation.
3. Training in practice: advanced optimisation algorithms, normalisation and regularisation.
4. Convolutional Neural Networks (CNNs): principles and basic operations, modern CNN architectures.
5. Recurrent Neural Networks (RNNs): principles, variants (e.g., LSTM, GRU).
6. Transformers: attention, architectural principles.
7. Large Language Models (LLMs): pre-training, fine-tuning.
8. Autoencoders: principles, variational autoencoders.
9. Generative models: Generative Adversarial Networks (GANs), diffusion models.
10. Trustworthy deep learning: robustness, explainability.

20 hours of lectures and 15 hours of classes in the Winter Term.

This course has a reading week in Week 6 of Winter Term.

This course will be delivered through a combination of classes, and lectures and Q&A sessions totalling a minimum of 35 hours across WT.

Students will work on on 8 problem sets in the WT, receiving optional feedback via email or in class.

• Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016, https://www.deeplearningbook.org/
• Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola, Dive into Deep Learning, https://d2l.ai/
• TensorFlow – An end-to-end open source machine learning platform, https://www.tensorflow.org/

Continuous assessment (10%) in Winter Term Week 5.

Continuous assessment (10%) in Winter Term Week 11.

Project (80%).

Two of the problem sets submitted by students weekly will be assessed (20% in total). Each problem set will have an individual mark of 10% and submission will be required in WT Weeks 5 and 11. In addition, there will be a take-home exam (80%) in the form of a group project in which they will demonstrate their ability to develop, train and evaluate neural network algorithms for solving a task of their choice.