How to debug machine learning models, from Apple to startup-Gabriel Bayomi-theDataScientistShow#055

preview_player
Показать описание


0:00 Intro
00:01:39 How he got into machine learning
00:06:43 His experience at Apple, Siri
00:15:55 How to validate the solution
00:19:39 Benefits of using external error analysis framework
00:21:30 How to build a model evaluation pipeline
00:28:26 Don’t overfit the subset of data
00:33:19 Your validation set shouldn’t be fixed
00:41:03 Become one with data
00:44:05 Three model interpretability library you should use
00:50:47 Common mistakes people made in model validation
00:53:33 How to create an adversarial test
00:55:43 How to check data quality
01:06:46 Transition from engineer to executive
01:10:04 Things he learnt from his favorite coworker
01:17:57 how job roles would evolve
Рекомендации по теме
Комментарии
Автор

Really helpful discussion for the students starting their carreer in ML.

jitendrakumar-clko
Автор

Fantastic Gabriel
AI & ML is a field that's picked a lot of my interest lately. Hope to engage with you sometimes soon.

kayodekalejaiye