COMP219: Advanced Artificial Intelligence (2018/2019)

Staff

• Dr Xiaowei Huang (Lecturer)
• Mr Jacopo Castellini (Demonstrator)
• Mr Cameron Hargreaves (Demonstrator)
• Ms Elektra Kypridemou (Demonstrator)
• Mr Themistoklis Melissourgos (Demonstrator)

Office Time

• Wednesday 11:00 - 12:00
• Thursday 14:00 - 15:00

Aims

• To equip students with the knowledge about basic algorithms that have been used to enable the AI agents to conduct the perception, inference, and planning tasks;
• To equip students with the knowledge about machine learning algorithms;
• To provide experience in applying basic AI algorithms to solve problems;
• To provide experience in applying machine learning algorithms to practical problems;

Learning Outcomes

• Ability to explain in detail how the techniques in the perceive-inference-action loop work
• Ability to choose, compare, and apply suitable basic learning algorithms to simple applications
• Ability to explain how deep neural networks are constructed and trained, and apply deep neural networks to work with large scale datasets
• Understand reinforcement learning, and is able to develop deep reinforcement learning algorithms for suitable applications

Lectures

• lecturer1 , with video stream available from here
• lecturer2 , with video stream available from here
• lecturer3 , with video stream available from here
• lecturer4 , with video stream available from here
• lecturer5 , with video stream available from here
• lecturer6 , with video stream available from here
• lecturer7 , with video stream available from here
• lecturer8 , with video stream available from here
• lecturer9 , with video stream available from here
• lecturer10 , with video stream available from here
• lecturer11 , with video stream available from here
• lecturer12 , with video stream available from here
• lecturer13 , with video stream available from here
• lecturer14 , with video stream available from here
• lecturer15 , with video stream available from here
• lecturer16 , with video stream available from here
• lecturer17 , with video stream available from here
• lecturer18, with video stream available from here
• lecturer19, with video stream available from here
• lecturer20, with video stream available from here
• lecturer21, with video stream available from here
• lecturer22, with video stream available from here
• lecturer23, with video stream available from here
• lecturer24, with video stream available from here
• lecturer25, with video stream available from here
• lecturer26, with video stream available from here
• lecturer27, with video stream available from here
• lecturer28, with video stream available from here

Tutorials:

• Week 2: Chapter 1
• Exercise and Code and ipynb Code
• Week 3: Chapter 2, the first two sections, up to page 32
• Exercise and Code
• Week 4: Chapter 3, Choosing a classification algorithm, first step with scikit-learn, and modeling class probabilities via logistic regression
• Exercise and Code
• Week 5: Chapter 3, maximum margin classification with support vector machine, and solving nonlinear problems using a kernel SVM
• Exercise and Question Code and Answer Code
• Week 6: Chapter 3, deicison tree learning, and k-nearest neighbors
• Exercise and Question Code and Answer Code
• Week 7: Chapter 12
• Exercise and Question Code and Answer Code

Assignments:

• Assignment1
• Assignment2

TextBooks:

• Christopher Bishop, Pattern Recognition and Machine Learning, Springer-Verlag New York, 2006.
• Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press. 2017
• Sebastian Raschka. Python Machine Learning. Packt Publishing. 2016.