ST456 Half Unit
Deep Learning
This information is for the 2025/26 session.
Course Convenor
Prof Milan Vojnovic
Availability
This course is available on the MPA in Data Science for Public Policy, MSc in Applied Social Data Science, MSc in Data Science, 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, MSc in Statistics (Financial Statistics), MSc in Statistics (Financial Statistics) (Research), MSc in Statistics (Research), MSc in Statistics (Social Statistics) and MSc in Statistics (Social 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.
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 10.00am on Friday 26 September 2025.
Course lecturers will aim to make initial offers to students on LSE For You by Friday 26 September.
For queries contact: Stats-Msc@lse.ac.uk
MSc Data Science students will be given priority for enrollment in this course.
Requisites
Additional requisites:
The course requires some mathematics, particularly basic concepts of linear algebra, and expects a basic knowledge of computer programming, primarily in Python.
Course content
This course is about deep learning, covering fundamental concepts of deep learning, neural networks, training and evaluation methods, and neural network architectures designed for tasks such as prediction and generative models for images, sequences, natural language processing, and large language models. The course will cover the following topics:
- Introduction: course overview
- Introduction to neural networks: single-layer networks, linear discriminant functions, XOR problem, perceptron, multi-layer perceptron, perceptron learning criteria, perceptron learning algorithm, feedforward neural network architecture
- Optimisation algorithms: empirical loss function minimisation, gradient descent algorithm, stochastic gradient descent algorithm
- Advanced optimisation algorithms: adaptive learning rates, momentum, backpropagation, dropout
- Convolutional neural networks (CNNs): principles and basic operations of convolutional neural networks, LeNet example
- Modern convolutional neural networks: understanding principles of modern CNN architectures, including AlexNet, VGGNet, NiN, GoogLeNet, ResNet, and DenseNet
- Recurrent neural networks (RNNs): RNN models, training RNNs, gated RNNs, GRU, LSTM, Deep RNNs, bidirectional RNNs, vector to sequence models using RNNs
- Sequence to sequence models: machine translation tasks, encoder-decoder architecture, attention mechanisms, transformer, large language models
- Autoencoders: introduction to autoencoders, linear factor models, PCA and probabilistic PCA, sparse coding, autoencoders, variational autoencoders
- Generative adversarial networks (GANs): introduction to GANs, GAN architecture and training, Wasserstein GANs, Wasserstain GANs with gradient penalty
Teaching
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.
Formative assessment
Students will be expected to produce 8 problem sets in the WT.
Indicative reading
- 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/
Assessment
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.
Key facts
Department: Statistics
Course Study Period: Winter Term
Unit value: Half unit
FHEQ Level: Level 7
CEFR Level: Null
Total students 2024/25: 100
Average class size 2024/25: 17
Controlled access 2024/25: NoCourse selection videos
Some departments have produced short videos to introduce their courses. Please refer to the course selection videos index page for further information.
Personal development skills
- Self-management
- Problem solving
- Application of information skills
- Communication
- Application of numeracy skills
- Commercial awareness
- Specialist skills