medical / technology / education / art / flub
"This paper proposes a checklist for reporting on AI systems, and covers the initial protocols and scoping, modelling and code, algorithm design, training data, testing and validation, usage, comparisons, real-world requirements, results and limitations, and ethical considerations. The aim is to have a systematic reporting process so that readers can have a comprehensive understanding of the AI system that was used in the research."
The AITEL reporting checklist.
Part 1: Protocols and scoping
Part 2: Modelling and code
Part 3: Algorithm design
Part 4: Training data (if M-L)
Part 5: Testing/validation (new systems)
Part 6: Use/testing/validation (known systems)
Part 7: Comparisons (if comparisons are made)
Part 8: Real-world requirements
Part 9: Results
Part 10: Discussion
Part 11: Ethics
Source: www.tandfonline.com
Image by StockSnap from Pixabay
reporting checklist part comparisons validation aitel testing protocols