How to Build Deep Learning Models

As the data world undergoes its cambrian explosion phase our data tools need to become more advanced to keep pace. Deep Learning has emerged as a key tool in the non-linear arms race of machine learning. Applications in text, sensor processing (IoT), image processing, and audio processing have all emerged as prime deep learning applications. In this session we will take a look at a practical review of what is deep learning and how DL4J’s architecture allows the Fortune 500 to easily build deep learning models with large amounts of data on Hadoop and Spark. We’ll also look at practical workflows for building next-generation applications with the DL4J tool suite.

Josh Patterson is the Director of Field Engineering at Skymind, a company that provides deep learning tools for use with Hadoop and Spark. Josh is a co-creator of the Deeplearning4j framework as well as the co-author of Oreilly’s “Deep Learning: A Practitioner’s Approach” due out in late 2016. Before Skymind, Josh held senior architecture roles at Cloudera (2010-2013). With extensive experience in Deep Learning systems architecture for customers across diverse industries ranging from healthcare to telecom, Josh has experience in real world data science deployments across the Fortune 500 for systems such as fraud detection, text analytics, image recognition, and IoT pattern analysis.