All videos
Opera view

The reasons we do not do Machine Learning any more.

October 8, 2019

Last year I was talking how back at AirHelp we use machine leaning. As an example I have used the classical problem: analyzing the pictures with convolutional neural networks. This season I'd like to tell you when we decide that the ML approach is the wrong choice.I will share the story of what has happened to this CNN we have created last year.

Tags

Data Machine Learning

About the speaker

Michał Jakóbczyk

Michał Jakóbczyk

Software Engineering Director at Airhelp
Primarily I'm a Software Engineer. For last fifteen years doing Big Data, data analysis, machine learning, product and project management. For last several years focused…
Read more

Other videos that you might like

fallback image
Data
Collaborative Filtering Microservices on Spark
Rui Vieira, Sophie Watson
fallback image
Data
How we built a Shiny App for 700 users?
Olga Mierzwa-Sulima
fallback image
AI
Data
ART 360: Defending AI models against adversarial attacks
Mathieu Sinn
fallback image
Data
From Spark MLlib model to learning system with Watson Machine Learning
Łukasz Ćmielowski
All videos