Module Descriptors
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
ELEC71090
Key Facts
Digital, Technology, Innovation and Business
Level 7
15 credits
Contact
Leader: Masum Billah
Email: masum.billah@staffs.ac.uk
Hours of Study
Scheduled Learning and Teaching Activities: 48
Independent Study Hours: 102
Total Learning Hours: 150
Assessment
- Coursework - Research based - 3000 words weighted at 50%
- Exam (time constrained practical under exam conditions) weighted at 50%
Module Details
Module Indicative Content
- The Foundations of Artificial Intelligence.
- The History of Artificial Intelligence.
- Key Principles of Artificial Intelligence.
- Problem solving.
- Knowledge and reasoning.
- Uncertain knowledge and reasoning.
- Different types of Learning.
- Agents of communicating, perceiving, and acting.
- Practical Natural Language Processing.
- Artificial Intelligence, machine learning and deep learning algorithms.
- Understand Artificial Intelligence/Deep Learning techniques and their application to solve real-life problems.
- Artificial Intelligence and Smart technologies.
- Robots and Artificial Intelligence (Components, Aspects, Applications, etc).
- Computer Visions, Pattern recognition, and Robotics.
- Hybrid Intelligent systems.
- Ethical and legal issues related to Artificial Intelligence systems
- The History of Artificial Intelligence.
- Key Principles of Artificial Intelligence.
- Problem solving.
- Knowledge and reasoning.
- Uncertain knowledge and reasoning.
- Different types of Learning.
- Agents of communicating, perceiving, and acting.
- Practical Natural Language Processing.
- Artificial Intelligence, machine learning and deep learning algorithms.
- Understand Artificial Intelligence/Deep Learning techniques and their application to solve real-life problems.
- Artificial Intelligence and Smart technologies.
- Robots and Artificial Intelligence (Components, Aspects, Applications, etc).
- Computer Visions, Pattern recognition, and Robotics.
- Hybrid Intelligent systems.
- Ethical and legal issues related to Artificial Intelligence systems
Module Learning Strategies
Lectures / tutorials - 24 hours
Practical laboratory work - 24 hours
The lectures will focus on real life application of Artificial Intelligence. Group learning will be encouraged.
The tutorials will be run as a question answer session away from the computers where students can ask specific questions or work on example problems.
Module Texts
Brady M., et al., (2012), Robotics and Artificial Intelligence, Springer Berlin Heidelberg.
Stuart J., et al., (2009), Artificial Intelligence: A Modern Approach, Prentice Hall, New Jersey, 3rd edition.
Tom M., et al., (2017), Machine Learning, McGraw Hill Education; New York.
Goodfellow I., et al., (2017), Deep Learning (Adaptive Computation and Machine Learning Series). MIT Press, Cambridge, Massachusetts.
Shalev-Shwartz S., et al., (2014), Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, Cambridge, England.
Stuart J., et al., (2009), Artificial Intelligence: A Modern Approach, Prentice Hall, New Jersey, 3rd edition.
Tom M., et al., (2017), Machine Learning, McGraw Hill Education; New York.
Goodfellow I., et al., (2017), Deep Learning (Adaptive Computation and Machine Learning Series). MIT Press, Cambridge, Massachusetts.
Shalev-Shwartz S., et al., (2014), Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, Cambridge, England.
Module Resources
PCs running MATLAB and LabVIEW.
PCs with interface cards
Robot arm
Library resources (books, journals accessible online, full IEEE Xplore access to academic papers, and various magazines)
PCs with interface cards
Robot arm
Library resources (books, journals accessible online, full IEEE Xplore access to academic papers, and various magazines)
Learning Outcomes
1. Demonstrate a deep systematic understanding and critical evaluation of the application of Artificial intelligence and Machine learning. [AHEP 3: SM7M, SM8M,]
2. Analysing complex real-life problems and apply appropriate analytical approach, experimental and simulation techniques to solve these problems using Artificial Intelligence tools. [AHEP 3: SM8M, EA5m EA6M, D9M, D10M, G1]
3. Critically evaluate and compare the possible solutions of the investigated complex problems. [AHEP 3: EA5m ,EA6M, D9M]
4. Plan, design, develop and present an optimised set of resources for a desired application. [AHEP 3: EA6M, D10M, D11M, G1]
2. Analysing complex real-life problems and apply appropriate analytical approach, experimental and simulation techniques to solve these problems using Artificial Intelligence tools. [AHEP 3: SM8M, EA5m EA6M, D9M, D10M, G1]
3. Critically evaluate and compare the possible solutions of the investigated complex problems. [AHEP 3: EA5m ,EA6M, D9M]
4. Plan, design, develop and present an optimised set of resources for a desired application. [AHEP 3: EA6M, D10M, D11M, G1]
Assessment Details
A COURSEWORK weighted at 50%.
A practical based exam length 2 hours weighted at 50%.
1) One coursework weighted at 50%. The coursework consists of a 2,000-word report on laboratory-based work to design and implement a suitable Artificial Intelligence-based solution for a real-life problem, which will assess learning outcomes 2 and 4. Meeting AHEP 3 Outcomes SM8M, EA5m, EA6M, D9M, D10M, D11M, G1.
2) Two hour written examination weighted at 50%, which will assess learning outcomes 1 and 3. Meeting AHEP 3 Outcomes SM7M, SM8M, EA6M, EA5m, D9M.
A practical based exam length 2 hours weighted at 50%.
1) One coursework weighted at 50%. The coursework consists of a 2,000-word report on laboratory-based work to design and implement a suitable Artificial Intelligence-based solution for a real-life problem, which will assess learning outcomes 2 and 4. Meeting AHEP 3 Outcomes SM8M, EA5m, EA6M, D9M, D10M, D11M, G1.
2) Two hour written examination weighted at 50%, which will assess learning outcomes 1 and 3. Meeting AHEP 3 Outcomes SM7M, SM8M, EA6M, EA5m, D9M.