FM1AZCI75 Computational Intelligence
FM1AZCI75 Computational Intelligence
- Course description
- Course codeFM1AZCI75
- Level of study5.1
- Program of studyApplied Machine Learning
- Credits7.5
- Course coordinatorLeon Grobbelaar
The course provides knowledge of machine learning algorithms for classification, clustering, and regression problems. Candidates learn methods for improving the accuracy of the machine learning models and to further problem-solving practical and theoretical computational issues. The course also provides skills to study machine learning models to evaluate and optimise the application.
This course is relevant to the program because it will teach the students how to choose and apply the appropriate machine learning algorithm and tools to any given data-driven real-world problem. Also, students will acquire hands-on experience designing machine learning tools for industrial applications.
The candidate:
- has knowledge of processes and tools that are used to create machine learning algorithms
- has knowledge of concepts, processes and tools that are used to compare machine learning algorithms
- has insight into relevant regulations, standards and principles governing machine learning and computational intelligence
- can update his/her knowledge about existing machine learning computational models
The candidate:
- can apply knowledge of problem-solving to practical and theoretical computational problems
- masters tools and techniques related to machine learning algorithms
- masters tools and techniques to prepare data for machine learning applications
- can find information and material that is relevant to machine learning algorithms and technologies
- can study machine learning models and identify issues and evaluate the results
The candidate:
- has developed an understanding of the importance and relevance of machine learning and its applications
- can carry out machine learning projects through planning, implementation, evaluation and presentation of the outcomes
- can develop work methods based on the application of machine learning to given situations
In this course, the following teaching and learning methods can be applied, but are not limited to:
- Lecture: Educator-led presentations or activities providing knowledge, skills, or general competencies in the subject area.
- Group work: Collaborative activities where students work together to solve problems or complete tasks.
- Tutoring: One-on-one or small group sessions with an instructor for personalized guidance and support.
- Student presentations: Opportunities for students to demonstrate their understanding of course material by presenting to peers.
- Online lessons: Digital content delivered via an online learning platform.
- Guidance: Individualized advice and direction from instructors to support students in their learning journey.
- Workshops: Practical sessions focused on hands-on application of theoretical concepts or skills.
- Self-study: Independent study where students engage with course material on their own without any teacher support.
Teaching materials, reading lists, and essential resources will be shared in the learning platform and software user manuals where applicable.