The Fifth Elephant 2019

Gathering of 1000+ practitioners from the data ecosystem

Tickets

BoF on Interpretability of ML Models

Submitted by Namrata Hanspal (@namrata4) via Abhishek Balaji (@booleanbalaji) on Monday, 15 July 2019

Session type: Birds of a Feather session of 1 hour Session type: BOF session of 1 hour

View proposal in schedule

Abstract

Complex machine learning models work very well at prediction and classification tasks but become really hard to interpret. On the other hand simpler models are easier to interpret but less accurate and hence oftentimes we are made to take a call between interpretability and accuracy.

Key takeaway

Understand why an ML algorithm makes a particular decision which can help make better business decisions.

Outline

  • Why is model interpretability important?
  • Trade off between accuracy and interpretability.
  • Developments in explainable AI.
  • Interpret black box models, global and local interpretation.

Requirements

Who should attend?

Anyone into ML and who wishes to understand blackbox(ML) decisions.

What should you know?

Basics of Machine learning and statistics.

Speaker bio

Facilitators:

  • Namrata Hanspal
  • Fathat Habib
  • Aditya Patel

Comments

Login with Twitter or Google to leave a comment