Visit UNICEF Global
The following is an editable version of the model card proposed in arxiv.org/abs/1810.03993.
Basic information about the model.
Use cases that were envisioned during development.
Factors could include demographic or phenotypic groups, environmental conditions, technical attributes, or others.
Metrics should be chosen to reflect potential real-world impacts of the model.
Details on the dataset(s) used for the quantitative analyses in the card.
May not be possible to provide in practice. When possible, this section should mirror Evaluation Data. If such detail is not possible, minimal allowable information should be provided here, such as details of the distribution over various factors in the training datasets.
Quantitative analyses should be broken down by the chosen factors.
In this section, you should explore and document the following:
This section should list additional concerns that were not covered in the previous sections.
To be written.
Updated on 21 Jun 2022
Recommendations for building AI policies and systems that uphold child rights. Part of UNICEF AI for children project.
Assessing common AI/ML mistakes that lead to unintended side effects.
How do you document your machine learning development process? This guide shares transparency best practices.