Home / Certificates / CPP-36
Professional Certificate · Master's level · CPP-36
Fairness, Robustness and Explainability of Models
For: Data specialists, developers, auditors and compliance officers who evaluate artificial intelligence systems before or after they are put into service.
Learning outcomes
- Evaluate the fairness of an artificial intelligence system across groups.
- Evaluate a model's robustness to perturbations and its uncertainty.
- Write the report evaluating a model's fairness, robustness and explainability.
Programme over 4 weeks
| Week | Content |
|---|---|
| Week 1 | Evaluation beyond accuracy: fairness across groups, robustness to perturbations, uncertainty, explainability. |
| Week 2 | Fairness across groups: measurement on a model and dataset provided, in a virtual lab; critical reading of the results. |
| Week 3 | Robustness to perturbations, uncertainty and explainability; robustness tests conducted in the programme's isolated lab. |
| Week 4 | Professional simulation: report evaluating the fairness, robustness and explainability of a model provided. |
Assessment
Marked professional simulation in a virtual lab, assessed against a rubric (70%): evaluation report on a model provided; online knowledge-check quiz (30%). Tests conducted only in the programme's isolated lab, on fictitious or anonymised data.
The certificate is awarded with a mark of at least 10 out of 20.
Optional: Documentation and Transparency of Artificial Intelligence Systems
An additional 1-credit module over 2 weeks (CPP-36C), awarded as a separate certificate; together with this certificate, it makes up the full course component of the original programme.
- Model cards and system registers.
- Informing the people concerned, means of redress; accessibility of interfaces.
At your own pace: the self-paced pathway
In a class, this certificate takes 4 weeks, on the cohort's dates. On the self-paced pathway, you start whenever you like, online, and progress at your own pace. The price is the same.
Estimate how long my pathway will take
- Duration
- about 4 weeks
- Estimated end
- 4 weeks after you start
- Examination
- Online, subject to available slots, no earlier than 4 weeks after you start
- Payment
- In a single payment
An indicative estimate, for a start today and 40 hours of work. You can change your pace along the way; the pathway must be completed within 12 weeks (about 3 months) of your start. Your e-Campus access opens with your first payment.
Admission
Basic knowledge of machine learning and programming experience (Bachelor's degree level or equivalent experience assessed on application). Admission based on application; detailed requirements set by the school.
The credits you earn are recognised without further assessment if you later join the programme they come from, Professional Master's degree in Artificial Intelligence, within a period set by the certificate regulations.