MODULE DETAILS |
Module 16: Machine Learning and Artificial Intelligence DMCMAI616
Nominal duration: 5 weeks (60 hours total time commitment) This time commitment includes the structured activities, preparation reading, and attendance at each webinar, completing exercises, practical assessments and proctored assessments. It is also expected that students spend additional time on readings, personal study, independent research and learning, practicing on remote labs and required software and working on any projects and assignments. This module covers the basics of machine learning and Artificial Intelligence. |
MODULE PURPOSE |
The purpose of this module is for the participants to develop fundamental knowledge of computational statistics, mathematical optimization, machine learning and artificial intelligence (A.I.). |
MODIFICATION HISTORY | Version 2.0 |
PRE-REQUISITE MODULES/UNIT(S)
|
Modules that must be delivered and assessed before this module: Machine Vision DMCMVI609 Design Closed Loop Motion Control Systems DMCMCS610 Modules that must be delivered concurrently with this module: N/A |
ASSESSMENT STRATEGY |
METHODS OF ASSESSMENT Assessors should gather a range of evidence that is valid, sufficient, current and authentic. Evidence can be gathered through a variety of ways including direct observation, supervisor's reports, project work, structured assessments, samples and questioning. This will include short answer questions on the knowledge content, the use of remote and virtual labs, and writing tasks to apply the learning to academic tasks. CONDITIONS OF ASSESSMENT Assessors must:
Questioning techniques should not require language, literacy and numeracy skills beyond those required in this module. The candidate must have access to all tools, equipment, materials and documentation required. The candidate must be permitted to refer to any relevant workplace procedures, product and manufacturing specifications, codes, standards, manuals and reference materials. Assessments will be open book assessment and may be completed off-campus. Invigilation software will be used for some assessments to ensure authenticity of work completed. Model answers must be provided for all knowledge-based assessments to ensure reliability of assessment judgements when marking is undertaken by different assessors. |
SUMMARY OF LEARNING OUTCOMES |
|
Learning Outcome 1 | Solve problems using search algorithms |
Assessment criteria |
1.1. Describe basic search algorithms
1.2. Compare different search algorithms
1.3. Use a search algorithm in a problem-solving task |
Learning Outcome 2 |
Identify and explain Simultaneous Localization and Mapping (SLAM) |
Assessment criteria |
2.1. Describe robot localisation techniques and principles
2.2. Identify the basics of mathematical optimization
2.3. Explain the function and principles of particle filters and Kalman filters
2.4. Describe how particle filters and Kalman filters can be used in Simultaneous Localization and Mapping (SLAM) |
Learning Outcome 3 |
Outline machine learning basics |
Assessment criteria |
3.1. Describe machine learning applications and methodologies
3.2. Explain and compare different machine learning algorithms
3.3. Outline the steps to solve predictive/probability problems using machine learning |
Delivery Mode Online and/or face-to-face |
Software/Hardware Used
Software
-
MATLAB
- Simulink
Hardware
- Remote Lab