New beginnings. And the future of this Newsletter.
Six Months, one acquisition, and a handful of thoughts.
Santiago and the ML Models
Personal newsletter where I share what I'm learning, writing, and up to in the field of ML/AI
Dormant Last read · last published · next check
Read 1 day ago and current, but nothing has been published for 14 months.
Latest posts
2024 Year in Review
A review of 2024. What I did, what I learned, and what I want to do in 2025.
The Little Book of ML Metrics 👀
I'm writing a book on ML metrics.
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
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 know how my model's performance is doing.
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 performance when doing continuous retraining.
Temporal degradation framework and other ideas
Update on writing my Master's thesis in public. Excuses, sketches and first results.
Writing my master's thesis in public
Choosing a thesis project, finding a supervisor and next steps
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.