COMPM050 - Advanced Topics in Machine Learning
This database contains 2016-17 versions of the syllabuses. For current versions please see here.
Note: Whilst every effort is made to keep the syllabus and assessment records correct, the precise details must be checked with the lecturer(s).
|Code||COMPM050 (Also taught as: COMPGI13)|
The prerequisites are probability, calculus, linear algebra, COMPM055 Supervised Learning and COMPM056 Graphical Models.
Thore Graepel & guest lecturers from Google DeepMind - Koray Kavukcuoglu, Hado van Hasselt, Joseph Modayil and Marie Mulville
|Aims||To learn the fundamentals of machine-learning based artificial intelligence: 1) to understand fundamentals and practice of deep learning, 2) to understand methods for reinforcement learning, planning and control in sequential decision making processes, 3) to learn how to implement algorithms in TensorFlow.|
|Learning Outcomes||To gain in depth familiarity with the selected research topics, understand their theory and applications, be able to individually read, understand and discuss research papers in the field.|
- Introductions to deep learning, reinforcement learning, deep reinforcement learning, and TensorFlow.
- Basics of machine learning, including:
- linear models
- least-squares regression
- maximum likelihood
- regularization & cross-validation
- logistic regression
- Deep learning, including:
- neural networks and convolutional neural networks
- end-to-end learning
- recurrent networks
- generative models
- variational inference
- natural language processing
- Reinforcement learning, including
- Markov decision processes
- dynamic programming
- model-free prediction and control
- value function approximation and policy gradients
- deep reinforcement learning
- integrating learning and planning
- exploration and exploitation
Method of Instruction
Lectures, reading, presentation and associated class problems.
The course has the following assessment components:
- Written Examination (50%)
- Coursework Section (50%)
To pass this module, students must:
- Obtain an overall pass mark of 50% for all components combined.
- Reinforcement learning:
R. Sutton and A. Barto, An Introduction to Reinforcement Learning
C. Szepesvari, Algorithms for Reinforcement Learning
- Deep learning:
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning