The course is set as 2 days of theoretical, demo and hands-on activities + 1 optional day of hackathon/workshop on selected datasets. Alternatively, the course is also offered as 4 x half days of theoretical, demo and hands-on activities + half day of hackathon/workshop on selected datasets.
The course covers a wide range of topics as follows:
- data science methodology: CRISP-DM,
- machine learning types and tasks,
- exploratory data analysis,
- principal component analysis,
- machine learning model deployment,
- pitfalls to avoid when performing data science, and
- assurance of data-driven models and algorithms.
On completing the course, the participant will:
- have a better understanding of what is meant by Data Science or Machine Learning (i.e. DS/ML an analytic approach and not as a “magical black-box hype”),
- have understanding what type of problems are suited for machine learning,
- have some ideas about which types of problems in your own work are candidates for DS/ML approaches,
- have some kind of awareness on some machine learning pitfalls to avoid,
- have some experience in using the tools to get started,
- have insight into what value machine learning and data science can bring, and
- have motivation for further learning and development.
This course is suitable for:
- Engineers, scientists, programmers, software developers, and other relevant discipline graduates who would like to equip themselves with data science skills (i.e. this course is an excellent entry point), and
- Professionals who frequently handle internal and/or external data, as participants will be discovering the untapped potential of the data and the realising more value from their data
It is beneficial if the participant has prior coding/programming experience, however this is not a pre-requisite. We are ready to customize the course and the tools to accommodate participants with no coding experience.
Private training sessions for corporates can be arranged on request.