Introduction to Transparent Machine Learning

Introducing the essentials on transparent machine learning for learners of diverse backgrounds to understand and apply transparent machine learning in real-world applications with confidence and trust.

Duration

31 - 40 hours

Level

Learner

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.

Details

Primary topics

Module Name

Topic

Chapter 1 (System and Process) Introduction to machine learning and transparency
Chapter 2 (System) Linear regression
Chapter 3 (System) Logistic regression
Chapter 4 (Process) Hypothesis testing and software development
Chapter 5 (Process) Cross validation and bootstrap
Secondary topics

Module Name

Topic

Chapter 6 (System and Process) Feature selection and regularisation
Chapter 7 (System and Process) Trees and ensembles
Chapter 8 (System) Generalised linear models and support vector machines
Chapter 9 (System) Principal component analysis and K-means/hierarchical clustering
Chapter 10 (System) Neural networks and deep learning

Instructors

Shuo Zhou

Academic Fellow in Machine Learning, University of Sheffield