Series

Use AutoML to find and deploy the best models in minutes

Learn how Watson AutoAI, the next-gen AutoML, discovers and builds modeling pipelines best suited for your data

Save Like

By Multiple authors
Updated October 9, 2020 | Published July 7, 2020

Automated Machine Learning (AutoML) tools help in automating the end-to-end process that is involved in building and maintaining machine learning models. In this series, learn how AutoAI in Watson Studio can automatically prepare data, apply machine learning algorithms, perform hyperparameter optimization, and build model pipelines best suited for your data sets and use cases.

Try a Coursera trial to learn about, and become certified on, rapid prototyping with Watson AutoAI. To connect with your peers and discuss AutoML and other data science topics, join the IBM Data Science Community.

Topic Description
Introduction to Watson AutoAI Learn how AutoAI is next-gen AutoML
Compare model building with and without AutoML Learn how AutoAI simplifies your model building experience
Generate the optimal model pipeline for your problem Get details on generating model pipelines
Auto-generate a Python notebook using AutoAI Generate, build, and deploy models from within a Python notebook
Quickly create your Python machine learning web app Automate all of the tasks involved in building predictive models for different requirements
Explore automated feature engineering for relational data Perform feature engineering tasks automatically and in minutes with IBM AutoAI in IBM Cloud Pak for Data

Introduction to Watson AutoAI

Blog

Next-gen AutoML with Watson AutoAI

July 7, 2020

Learn about:

  • Overview of Automated Machine Learning(AutoML)
  • Introduction to AutoAI

Compare model building with and without AutoML

Article

Build machine learning models with and without AutoML

October 21, 2020

Learn about:

  • Overview of Automated Machine Learning (AutoML)
  • Two ways to build predictive models, both with and without the help of AutoAI
  • Compare model building with and without AutoAI

Generate the optimal model pipeline for your problem

Tutorial

Generate machine learning model pipelines to choose the best model for your problem

August 19, 2019

Learn about:

  • Benefits of the AutoAI service on a use case
  • How tasks (feature engineering, model selection, and hyperparameter tuning) are performed
  • Details for choosing the best model among the pipelines and how to deploy and use these models

Auto-generate a Python notebook using AutoAI

Code pattern

Generate a Python notebook for pipeline models using AutoAI

September 30, 2020

Learn about:

  • Run an AutoAI experiment
  • Generate and save a Python notebook
  • Execute the notebook and analyze results
  • Make changes and retrain the model using Watson Machine Learning SDKs
  • Deploy the model using Watson Machine Learning from within the notebook

Quickly create your Python machine learning web app

Code pattern

Create a machine learning web app to predict your insurance premium cost

June 4, 2019

Learn about:

  • Quickly set up the services on IBM Cloud to build the model
  • Ingest the data and initiate the AutoAI process
  • Build different models using AutoAI and evaluate the performance
  • Choose the best model and complete the deployment
  • Generate predictions using the deployed model by making REST calls
  • Compare the process of using AutoAI and building the model manually
  • Visualize the deployed model using a front-end application

Explore automated feature engineering for relational data

Article

Explore automated feature engineering for relational data

March 15, 2021

Learn about:

  • Perform feature engineering automatically with IBM AutoAI in IBM Cloud Pak for Data
Legend

Related

Tutorial

Automate model building in IBM Watson Studio

December 17, 2020
Tutorial

Automate model building with AutoAI

June 23, 2020
Series

Learning path: Getting started with Watson Studio

September 3, 2019