|Fees||Look up fees|
Upon completion, students are expected to gain an overview of a major branch of artificial intelligence known as computational intelligence or soft computing, and their applicability to mechatronic systems. Students are expected to practice some of the methods they learn on real and synthetic data and appreciate the strengths and limits of the approaches they learn.
A variety of topics in computational intelligence are expected to be covered, with selections to be made from 1) neural networks including generative networks, deep neural networks and convolution neural networks, 2) learning methods including unsupervised learning, reinforcement learning and semi-supervised learning, 3) appreciation of other Computational Intelligence methods: fuzzy systems and evolutionary algorithms and 4) an introduction to stochastic dynamic programming and its relationship to AI. Mechatronic applications in broader terms and case studies from other relevant areas of engineering will be discussed.
Intended learning outcomes
At the conclusion of this subject students should be able to:
- Understand the concepts of Neural Networks and various types of learning algorithms
- Understand the concepts of artificial intelligence approaches to optimization
- Choose the best artificial intelligence approaches for various classes of real problems including engineering design and data centric modelling
- Implement and analyze the capability and limitations of artificial intelligence in engineering applications
- Application of knowledge of basic science and engineering fundamentals
Last updated: 3 November 2022