DataHour: How to Build a Multi Task Model using TensorFlow

DataHour: How to Build a Multi Task Model using TensorFlow

24 Mar 202313:03pm - 24 Mar 202314:03pm

DataHour: How to Build a Multi Task Model using TensorFlow

About the Event

Multi-Task Machine Learning models are a type of machine learning algorithm that can learn to perform multiple tasks simultaneously. These models are designed to handle complex problems that require multiple sub-tasks to be performed, and they can help improve the efficiency and accuracy of machine learning systems.

SHAP is a framework used for explaining the output of machine learning models. It can give us global feature importance as well as sample level explanations.

In this DataHour, Sateesh will explain how to build a Multi Task Model using TensorFlow and  get sample explanations with SHAP using a structured dataset.


Prerequisites:
 
Basic understanding of Machine Learning and TensorFlow and enthusiasm of learning Data Science.

  1. Best articles get published on Analytics Vidhya’s Blog Space
  2. Best articles get published on Analytics Vidhya’s Blog Space
  3. Best articles get published on Analytics Vidhya’s Blog Space
  4. Best articles get published on Analytics Vidhya’s Blog Space
  5. Best articles get published on Analytics Vidhya’s Blog Space

Who is this DataHour for?

  1. Best articles get published on Analytics Vidhya’s Blog Space
  2. Best articles get published on Analytics Vidhya’s Blog Space
  3. Best articles get published on Analytics Vidhya’s Blog Space

About the Speaker

Sateesh Sivakoti

Sateesh Sivakoti

ML Scientist at PayPal

Sateesh is currently working as an ML Scientist at PayPal and has about 3.5 years of experience, all in the field of Advanced Machine Learning. Prior to this he worked as a Data Science Associate Consultant in the Advanced Data Science organization at ZS Associates where he typically worked on building ML solutions for various marketing and customer lifecycle use cases. He has graduated with a Dual Degree in Aerospace Engineering from IIT Madras

Participate in discussion

Registration Details

5039

Registered

Become a Speaker

Share your vision, inspire change, and leave a mark on the industry. We're calling for innovators and thought leaders to speak at our event

  • Professional Exposure
  • Networking Opportunities
  • Thought Leadership
  • Knowledge Exchange
  • Leading-Edge Insights
  • Community Contribution