Unless you’ve been living under a rock for the past several years, you’ve probably heard of the promise of deep learning and seen reports saying how good it is for natural data, such as images, video, and natural language, and time series analytics. But what exactly is deep learning? How do you use it, and where should you start?
H2O—a fast, scalable, in-memory open source machine-learning platform that supports distributed deep learning on huge datasets that couldn’t be handled in a nondistributed environment—enables you to start your journey with deep learning in just a few clicks. Mateusz Dymczyk explains what deep learning is all about, outlines the many types of deep learning (and which of them H2O supports), and demonstrates how can you integrate H2O, Spark, and other frameworks such as Google’s TensorFlow to get access to other network types.
Mateusz Dymczyk is a Japan-based software engineer at H20.ai, where he works as a researcher on machine learning and NLP projects. Previously, he worked at Fujitsu Laboratories. Mateusz loves all things distributed and machine learning and hates buzzwords. In his spare time, he participates in the IT community by organizing, attending, and speaking at conferences and meetups. Mateusz holds an MSc in computer science from AGH UST in Krakow, Poland.
©2016, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org
Apache Hadoop, Hadoop, Apache Spark, Spark, and Apache are either registered trademarks or trademarks of the Apache Software Foundation in the United States and/or other countries, and are used with permission. The Apache Software Foundation has no affiliation with and does not endorse, or review the materials provided at this event, which is managed by O'Reilly Media and/or Cloudera.