Presented By O’Reilly and Intel Nervana
Put AI to work
September 17-18, 2017: Training
September 18-20, 2017: Tutorials & Conference
San Francisco, CA

In-Person Training
Neural networks for time series analysis using Deeplearning4j

Josh Patterson (Skymind), Susan Eraly (Skymind), Dave Kale (Skymind), Tom Hanlon (Skymind)
Sunday, September 17 & Monday, September 18, 9:00am - 5:00pm
Location: Franciscan C

Participants should plan to attend both days of this 2-day training course. Platinum and Training passes do not include access to tutorials on Monday.

Recurrent neural networks have proven to be very effective at analyzing time series or sequential data, so how can you apply these benefits to your use case? Josh Patterson, Susan Eraly, Dave Kale, and Tom Hanlon demonstrate how to use Deeplearning4j to build recurrent neural networks for time series data.

What you'll learn, and how you can apply it

  • Learn how to configure your dataset properly for use by the neural network, set appropriate hyperparameters for the neural network, configure your output layer for prediction and classification, and choose appropriate hardware

Prerequisites:

  • A working knowledge of at least one programming language (The labs will be performed in Java on a provided virtual machine.)

Hardware and/or installation requirements:

  • A laptop with 10 GB of available space and VirtualBox or VMware Player installed

Recurrent neural networks have proven to be very effective at analyzing time series or sequential data, so how can you apply these benefits to your use case? Josh Patterson, Susan Eraly, Dave Kale, and Tom Hanlon demonstrate how to use Deeplearning4j to build recurrent neural networks for time series data.

Outline

Day 1

  • Introduction to neural networks and an overview of the different types of neural networks (feed forward, convolutional, and recurrent)
  • Choosing the appropriate neural network for time series data
  • Hands-on lab: Generating weather forecasts with a recurrent neural network


Day 2

  • Configuring a data ingestion pipeline sequence data
  • Recurrent neural nets for the prediction of medical outcomes
  • Recurrent neural nets for the classification of sequence data
  • Hands-on lab: Sequence classification with recurrent neural networks

About your instructors

Photo of Josh Patterson

Josh Patterson is the director of field engineering for Skymind. Previously, Josh ran a big data consultancy, worked as a principal solutions architect at Cloudera, and was an engineer at the Tennessee Valley Authority, where he was responsible for bringing Hadoop into the smart grid during his involvement in the openPDC project. Josh is a cofounder of the DL4J open source deep learning project and is a coauthor on the upcoming O’Reilly title Deep Learning: A Practitioner’s Approach. Josh has over 15 years’ experience in software development and continues to contribute to projects such as DL4J, Canova, Apache Mahout, Metronome, IterativeReduce, openPDC, and JMotif. Josh holds a master’s degree in computer science from the University of Tennessee at Chattanooga, where he did research in mesh networks and social insect swarm algorithms.

Photo of Susan Eraly

Susan Eraly is a software engineer at Skymind, where she contributes to Deeplearning4j. Previously, Susan worked as a senior ASIC engineer at NVIDIA and as a data scientist in residence at Galvanize.

Twitter for susan_eraly
Photo of Dave Kale

David Kale is a deep learning engineer at Skymind and a PhD candidate in computer science at the University of Southern California (advised by Greg Ver Steeg of the USC Information Sciences Institute). David’s research uses machine learning to extract insights from digital data in high-impact domains, such as healthcare. Recently, he has pioneered the application of recurrent neural nets to modern electronic health records data. At Skymind, he is developing the ScalNet Scala API for DL4J and working on model interoperability between DL4J and other major frameworks. David organizes the Machine Learning and Healthcare Conference (MLHC), is a cofounder of Podimetrics, and serves as a judge in the Qualcomm Tricorder XPRIZE competition. David is supported by the Alfred E. Mann Innovation in Engineering Fellowship.

Photo of Tom Hanlon

Tom Hanlon is an instructor at Cloudera, where he delivers courses on the wonders of the Hadoop ecosystem. Before beginning his relationship with Hadoop and large distributed data, he had a happy and lengthy relationship with MySQL with a focus on web operations. He has been a trainer for MySQL, Sun, Percona.

Conference registration

Get the Platinum pass or the Training pass to add this course to your package.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

Comments

Kuppu Seshadhri | CONSULTANT
09/14/2017 1:01am PDT

Besides Virtual Box installed and . 10GB free space, are there any other software requirements or prep work to be done ahead of training day?