Hakim Elakhrass

Hakim Elakhrass

NannyML
Detecting silent failures in ML models
136 points

Forums

Ryan Gilbert

4yr ago

How quickly do you reach for your phone in the morning?

We are increasingly connected to our phones which can make it difficult to fully unplug or be present at times. Once you wake up to start your day, how quickly do you reach for your phone to check your mentions, emails, etc?
Davor Kolenc

4yr ago

What is your startup about in 20 words or less?

Treblle makes it super easy to understand what's going on with your APIs and the apps that use them. https://treblle.com/
Ryan Gilbert

4yr ago

Happy Monday! What are you working on this week?

What are you working on this week? Is there anything the PH community can help with?
Hakim Elakhrass

3yr ago

NannyML - OSS Python library for detecting silent ML model failure

NannyML estimates real-world model performance (without access to targets) and alerts you when and why it changed. The performance estimation algorithm, confidence-based performance estimation (CBPE), was researched by core contributors.
Hakim Elakhrass

3yr ago

NannyML Regression v0.8.0 - OSS Python library for detecting silent ML model failure

Detecting silent model failure. NannyML estimates performance for regression and classification models using tabular data. Alerts you when and why it changed. It is the only open-source library capable of fully capturing the impact of data drift on performance
Bogomil Shopov - Бого

4yr ago

🤔What are you building (April)

Maybe you are not ready yet to submit it oficially, but you are building something nice. Share it with the community and ask for help/feedback. Go!