Search:
Match:
2 results
Research#llm📝 BlogAnalyzed: Dec 29, 2025 08:05

Turning Ideas into ML Powered Products with Emmanuel Ameisen - #349

Published:Feb 17, 2020 22:02
1 min read
Practical AI

Analysis

This article summarizes a podcast episode featuring Emmanuel Ameisen, a machine learning engineer at Stripe and author of "Building Machine Learning Powered Applications." The discussion focuses on practical aspects of building ML-powered products, covering project structuring, debugging, model explainability, different model types, and post-deployment monitoring. The episode likely provides valuable insights for machine learning practitioners and those interested in the productization of ML models. The focus is on the practical application of ML, moving beyond theoretical concepts.
Reference

“The article doesn't contain a direct quote, but the core topic is about structuring end-to-end machine learning projects, debugging and explainability, model types, and post-deployment monitoring.”

PermalinkPractical AI
Research#machine learning📝 BlogAnalyzed: Dec 29, 2025 08:08

Automated Machine Learning with Erez Barak - #323

Published:Dec 6, 2019 16:32
1 min read
Practical AI

Analysis

This article from Practical AI features an interview with Erez Barak, a Partner Group Manager at Microsoft Azure ML. The discussion centers on Automated Machine Learning (AutoML), exploring its philosophy, role, and significance. Barak breaks down the AutoML process into three key areas: Featurization, Learner/Model Selection, and Tuning/Optimizing Hyperparameters. The interview also touches upon post-deployment use cases, providing a comprehensive overview of AutoML's application within the data science workflow. The focus is on practical applications and the end-to-end process.
Reference

“Erez gives us a full breakdown of his AutoML philosophy, and his take on the AutoML space, its role, and its importance.”

PermalinkPractical AI