Course overview
This course aims to address the priority of transparency in responsible AI. We will study both transparent machine learning systems/models and transparent machine learning processes. We will adapt classical machine learning textbooks and materials under this framework to give a fresh treatment that will be more accessible for learners from multiple disciplines, including engineering, science, social sciences, medical science, and humanities. This will greatly complement the existing Responsible AI training landscape in the UK and beyond. Specifically, this course will recast selected contents in a leading textbook into the perspective of system and process transparency under a recent AI transparency framework from the Alan Turing Institute on "AI in Financial Services". Transparent machine learning systems will cover fully transparent machine learning models such as linear regression and "semi-transparent" machine learning models such as deep learning. Transparent machine learning processes will cover machine learning model evaluation and software development methodologies such as cross validation and software development life cycle.
Course materials will open in a separate Jupyter Notebook.
This course has been commissioned as part of our open funding call for Responsible AI courses, with funding from Accenture and the Alan Turing Institute.
Who is this course for?
Learners from diverse backgrounds, preferably with knowledge and skills of basic mathematics (particularly probability and linear algebra) and Python programming for machine learning. We suggest those lacking such knowledge and skills to go through Prerequisites to pass the quiz there first.
Learning outcomes
By the end of this course, you will be able to :
- Demonstrate an understanding of the theoretical issues and wider context related to transparent machine learning systems and processes
- Describe the inner workings of a selected number of transparent machine learning algorithms with the capability of interpreting the modelling process and the input-output relationships
- Deploy a practical implementation of transparent machine learning systems and processes in a real-world setting using Python libraries such as scikit-learn
- Visualise, interpret, and explain transparent machine learning systems and processes in a real-world setting to help stakeholders understand these systems and processes
- Gain the skills to confidently apply machine learning to an area of work, regardless of background
License
This course is released under a CC BY 4.0 license.
Materials can also be found on GitHub.