Return to page

BLOG

H2O Driverless AI Updates

 headshot

By Venkatesh Yadav | minute read | April 25, 2019

Blog decorative banner image

We are excited to announce the new release of H2O Driverless AI  with lots of improved features.

Below are some of the exciting new features we have added:

Version 1.6.1 LTS (April 18, 2019) – Available here 

  • Several improvements for MLI (partial dependence plots, Shapley values)
  • Improved documentation for model deployment, time-series scoring, AutoViz and FAQs

Version 1.6.0 (April 5, 2019)

  • Improved import of string columns larger than 2GB
  • Stabilized AutoViz on Windows
  • Improved quantile binning in MLI
  • Plot global absolute mean Shapley values instead of global mean Shapley values in MLI
  • Improvements to PDP/ICE plots in MLI
  • Validated Terraform version in AWS Lambda deployment
  • Added support for NULL variable importance in AutoDoc
  • Made Variable Importance table size configurable in AutoDoc
  • Improved support for various combinations of data import options being enabled/disabled
  • CUDA is now part of distribution for easier installation
  • Security updates:
    • Enforced SSL settings to be honored for all h2oai_client calls
    • Added config option to prevent using LocalStorage in the browser to cache information
    • Upgraded Tornado server version to 5.1.1
    • Improved session expiration and autologout functionality
    • Disabled access to Driverless AI data folder in file browser
    • Provided an option to filter content that is shown in the file browser
    • Use login name for HDFS impersonation instead of predefined name
    • Disabled autocomplete in login form
  • Cleaned up various bugs

Please see links below for additional information on H2O Driverless AI:

Release Notes:

http://docs.h2o.ai/driverless-ai/latest-stable/docs/userguide/release_notes.html 

Webinars:

BrightTalk Channel 

Driverless AI Documentation:

http://docs.h2o.ai/driverless-ai/latest-stable/docs/userguide/index.html 

If you have any questions, please reach out to support@h2o.ai 

Thanks,
Venkatesh Yadav

 headshot

Venkatesh Yadav , VP of Engineering

Software Engineering Leader at heart with a focus on building great teams that delivers amazing products and customer happiness. Venkatesh serves H2O as VP of Engineering Services. He joined the company from Adobe Systems, where he held a number of positions in the Software Engineering and Leadership space including his latest role as Sr. Manager, Software Engineering and Product Management with primary focus on Master Data Management and Data Science. Venkatesh played an instrumental Engineering and Product Management leadership role as an “Entrepreneur in Residence” in the various key strategic programs and initiatives like Adobe@Adobe, Adobe.io and Adobe.Data. Experience of managing and working with teams across the globe in US, Canada, Switzerland, Romania, India with a focus on value creation. Prior to Adobe Systems Venkatesh has served technology companies in various engineering roles in companies like Philips, HP and IBM. Venkatesh holds a Bachelor of Commerce degree from Mumbai University India and has successfully completed Product Management program from UC Berkeley and General Business Administration and Management program from McGill University. Connect with Venkatesh (@venkateshai)