Santiago and the ML Models
Subscribe
Sign in
Home
Notes
Archive
About
I ran 580 model-dataset experiments to show that, even if you try very hard, it is almost impossible to know that a model is degrading just…
In my opinion, data drift detection methods are very useful when we want to understand what went wrong with a model, but they are not the right tools to…
Jun 3
•
Santiago Víquez
Share this post
I ran 580 model-dataset experiments to show that, even if you try very hard, it is almost impossible to know that a model is degrading just by looking at data drift results
santiviquez.substack.com
Copy link
Facebook
Email
Note
Other
June 2023
Continuous retraining and formalizing the model aging framework
Update on writing my Master's thesis in public. Formalizing the results of the temporal degradation framework and first results on the impact on model…
Jun 19, 2023
•
Santiago Víquez
Share this post
Continuous retraining and formalizing the model aging framework
santiviquez.substack.com
Copy link
Facebook
Email
Note
Other
Temporal degradation framework and other ideas
Update on writing my Master's thesis in public. Excuses, sketches and first results.
Jun 5, 2023
•
Santiago Víquez
1
Share this post
Temporal degradation framework and other ideas
santiviquez.substack.com
Copy link
Facebook
Email
Note
Other
March 2023
Writing my master's thesis in public
Choosing a thesis project, finding a supervisor and next steps
Mar 17, 2023
•
Santiago Víquez
3
Share this post
Writing my master's thesis in public
santiviquez.substack.com
Copy link
Facebook
Email
Note
Other
Monitoring Workflow for Machine Learning Systems
It's natural for ML models to degrade - a recent study published in Nature journal found that 91% of AI degrade in time.
Mar 6, 2023
•
Santiago Víquez
1
Share this post
Monitoring Workflow for Machine Learning Systems
santiviquez.substack.com
Copy link
Facebook
Email
Note
Other
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts