AI Systems Implementation - COMP8260

Overview

Students are presented during lectures with advanced Artificial Intelligence/Machine Learning techniques (such as genetic algorithms, support vector machines (SVMs), deep learning, neural networks, stochastic gradient decent, Q-Learning/Deep Q-learning, ensembles, neuroevolution), including aspects of implementation, hyper parameter tuning, scalability and parallelism.

Details

Contact hours

Contact hours: 31
Hours of private study: 119
Total hours 150

Method of assessment

This module will be assessed by 100% coursework.

Indicative reading

• Patrick D. Smith, "Hands-On Artificial Intelligence for Beginners: An introduction to AI concepts, algorithms, and their implementation", Packt Publishing, 2018
• M. Tim Jones, "Artificial Intelligence: A Systems Approach", Jones & Bartlett Learning, 2015
• C. Aggarwal. Neural Networks and Deep Learning: a textbook. Springer, 2018.
• Aurélien Géron, “Hands-on Machine Learning with Scikit-Learn and TensorFlow”, O'Reilly, 2017
• Sebastian Raschka, “Python Machine Learning”, 2nd Ed, Packt Publishing, 2017
• Ian Goodfellow, Yoshua Bengio and Aaron Courville. “Deep Learning”, MIT Press, 2016
• Sarah Guido, Andreas C. Müller, “Introduction to Machine Learning with Python”, O'Reilly, 2016
• Tom Mitchell, “Machine Learning”, McGraw Hill, 1997

Learning outcomes

1. Demonstrate a systematic understanding of techniques used to implement AI Systems, and their underpinning principles;
2. Evaluate critically alternative AI approaches according to quality/cost trade-offs;
3. Master the application of AI techniques to solve realistic and real-world problems, using appropriate programming languages and libraries (e.g., Python and Scikit-Learn);
4. Analyse and critically evaluate the obtained results in terms of quality/cost, and devise strategies to improve or replace them.