University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Debugging Machine Learning Code

Debugging Machine Learning Code

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Mateja Jamnik.

Join us on Zoom

Developing robust machine learning code is hard, but debugging it is even harder! When developing machine learning (ML) solutions for complex problems such as autonomous driving we tend to focus on the hard research problems and develop theoretical models whose implementation we take for granted. In practice, however, bugs always creep in. How do you detect bugs when working with multidimensional arrays containing millions of parameters? How do you identify sources of error when building dynamic computational graphs? In this talk I will provide an overview of the existing methods for debugging ML code and showcase the first of its kind visual 3D debugger which makes debugging deep learning models a breeze.

Bio: After finishing his PhD in AI & Robotics at the University of Edinburgh, Dr. Penkov led the motion prediction team at Five AI for more than 2 years. Currently, he is the CEO & co-founder of Efemarai whose mission is to bring software QA to machine learning.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity