WM919-15 Machine Intelligence and Data Science
Introductory description
The module introduces key concepts related to Machine Learning (ML) and Artificial Intelligence (AI). Through exploring Linear and Logistic Regression techniques, students will embark on learning critical skills to tackle more advanced Neural Networks architectures. Key focus will be made on data management workflow to enhance performance and robustness of ML algorithms. Relevant AI techniques that are widely used in development of automated vehicles and related areas will be explored including: Supervised and Unsupervised Learning, Artificial Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks.
Module aims
The aim is to equip students with a solid knowledge of key AI techniques pervasive to the development of advanced driving systems and related areas. The module will focus on practical aspects of AI where the students will gain a strong high level understanding of the underlying theory. The emphasis will be on Machine Learning and Deep Learning techniques that are at the nexus of the development of future technologies.
Outline syllabus
This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.
- A general overview of AI systems and their applications
- Data science basis for machine intelligence:
- Understanding experimental data and fitting
- Classification
- Deep learning systems
- Introduction to neural networks
- Convolutional neural networks
- Recurrent neural networks
- Tutorials on tools and examples
Learning outcomes
By the end of the module, students should be able to:
- Critique advanced AI architectures in a given operational design domain [AHEP:4, M1, M2, M4, M5, M7]
- Implement Machine Learning algorithms by mastering relevant tools [AHEP:4, M1, M2, M3, M4]
- Choose, develop and evaluate critically neural networks [AHEP:4, M1, M2, M3, M4, M5, M7]
- Critically analyse data sets and techniques to train and test machine learning algorithms [AHEP:4, M1]
- Demonstrate a critical understanding of Machine Learning algorithms and their architecture [AHEP:4, M1, M2, M3]
Indicative reading list
- GOODFELLOW, Ian; BENGIO, Yoshua; COURVILLE, Aaron. Deep learning (adaptive
computation and machine learning series). Adaptive Computation and Machine Learning
series, 2016, 800. - RUSSELL, Stuart Jonathan, et al. Artificial intelligence: a modern approach. Upper Saddle
River: Prentice hall, 2003. - URMSON, Chris, et al. Tartan racing: A multi-modal approach to the darpa urban
challenge. 2007. - GUTTAG, John V. Introduction to computation and programming using Python. Mit Press,
- SAMARASINGHE, Sandhya. Neural networks for applied sciences and engineering: from
fundamentals to complex pattern recognition. CRC Press, 2016. - ASIMOV, Isaac. I, Robot, Robot series. 1950.
A variety of up-to-date sources including:
- Latest government / UK Automotive Council roadmaps for autonomous vehicles
- Latest automotive legislation and standards
- Current academic research in the field of smart connected autonomous vehicles
View reading list on Talis Aspire
Subject specific skills
Basic knowledge of AI techniques that are widely used in development of automated vehicles and related areas, Deep Learning techniques that are heavily used, including: Supervised and Unsupervised Learning, Artificial Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks.
Transferable skills
Critical Thinking, Problem solving, Communication, Information literacy (research skills), Digital literacy, Professionalism
Study time
Type | Required |
---|---|
Lectures | 20 sessions of 1 hour (13%) |
Seminars | 1 session of 1 hour (1%) |
Tutorials | 9 sessions of 1 hour (6%) |
Private study | 60 hours (40%) |
Assessment | 60 hours (40%) |
Total | 150 hours |
Private study description
In-depth reading around the subject
Costs
No further costs have been identified for this module.
You must pass all assessment components to pass the module.
Assessment group A4
Weighting | Study time | Eligible for self-certification | |
---|---|---|---|
Assessed work as specified by department | 80% | 42 hours | Yes (extension) |
A collection of 3 to 4 problems depending on their length and complexity to be solved by students. |
|||
In-module assessment | 20% | 18 hours | No |
Based on self-study hours on basic concepts of Machine Learning and neural networks. |
Feedback on assessment
Individual written feedback. Formative assessment during tutorials and class quizzes.
There is currently no information about the courses for which this module is core or optional.