You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As a leader in ML research, I want to come up with a set of guidelines to improve and safeguard the industrial practices used in Machine Learning systems, so that we can guarantee the quality and the output of the systems are fully tested and can be reproducible.
To do this, I expect the said guidelines would be presented in the form of a checklist so that other ML researchers can develop a comprehensive test suite to test their own research projects.
I expect this checklist to cover every aspect in the ML end-to-end pipeline, including:
(Not complete, feel free to add)
Data Presence
Data Quality
Data Ingestion
Model Fitting
Model Evaluation
Artifact Testing
Also, I expect this checklist would be written in a format that can be read by both humans and machines. (e.g. YAML/TOML/JSON format)
As a leader in ML research, I want to come up with a set of guidelines to improve and safeguard the industrial practices used in Machine Learning systems, so that we can guarantee the quality and the output of the systems are fully tested and can be reproducible.
To do this, I expect the said guidelines would be presented in the form of a checklist so that other ML researchers can develop a comprehensive test suite to test their own research projects.
I expect this checklist to cover every aspect in the ML end-to-end pipeline, including:
(Not complete, feel free to add)
Also, I expect this checklist would be written in a format that can be read by both humans and machines. (e.g. YAML/TOML/JSON format)
Good to Have:
The text was updated successfully, but these errors were encountered: