Workshop: AutoML Core Concepts and Hands-On Exercise

Description
Speaker
In this workshop, we will cover the core concepts and techniques behind AutoML. We will dive deep into the state of the art methods applied to Neural Architecture Search and Hyper parameter Parametrization.
The talk will cover the fundamentals of the methods and how the different methods compare to each other.
We will then spend an hour on a hand-on workshop on how to apply AutoML to real-world problems. Specifically we will walk through how to cast a problem into a classification or regression problem and then use AutoML to solve it. We will finally showcase how the AutoML solution performs as well as a hand-tuned solution.

The interactive workshop offer both theoretical and practical modules. By participating in the workshop you would be able to:

  • Learn the core concepts behind autoML
  • Building deep learning models using autoML with hands-on exercise
  • Build a system with AutoML and deploy to production

  • Agenda (US pacific time UTC-7):
  • [10:00 - 10:10am] Welcome and workshop overview
  • [10:10 - 10:45am] Core concepts behind AutoML - Neural Architecture Search and Hyperparameter Optimization
  • [10:45 - 11:45am] Hands on AutoML workshop
  • [11:45 - 12:00pm] Q&A and wrap up
  • Bindu&Colin

    Colin White, Research Scientist at RealityEngines.AI. He has publications in top machine learning conferences such as NeurIPS, COLT, and AISTATS. Colin received his Ph.D. in computer science from Carnegie Mellon University.

    Bindu Reddy CEO and Co-Founder of RealityEngines.AI. she was the General Manager for AI Verticals at AWS, AI. Her organization created and launched Amazon Personalize and Amazon Forecast, the first of their kind AI services that enable organizations to create custom deep-learning models easily. Prior to that, she was the CEO and co-founder of Post Intelligence that was acquired by Uber. Bindu was previously at Google

    • Date: May 28, 10:00 (US Pacific Time)
    • Fee: Free
    • Available Seats: 0 (max 325)
    • Help? Send Question
    Watch Recording