Up and Running with Deep Learning

Video description

Quickly dive-in to the most current topics in the field of deep learning, with this curated collection from Strata + Hadoop World 2016. This video features presentations from speakers in both academia and industry, covering the essentials of deep learning, and how to use the latest tools and techniques. Viewers will learn:

  • Benefits of deep learning over other machine learning techniques
  • Advances in the field
  • Elements of deep learning workflows, including how to address common challenges
  • How to handle large-scale distributed training of neural networks, using TensorFlow
  • A scalable implementation of deep neural networks for Spark
  • How to use SparkNet to construct deep networks using existing libraries

Publisher resources

View/Submit Errata

Table of contents

  1. Creating Intelligence: An Applications-First Approach to Machine Learning
    1. The State of Machine Learning Today - Carlos Guestrin (Dato, Inc.)
    2. Intelligent Applications Using Machine Learning - Carlos Guestrin (Dato, Inc.)
    3. Thinking in Terms of Apps, Not Algorithms - Carlos Guestrin (Dato, Inc.)
    4. Making Machine Learning Simple to Use - Carlos Guestrin (Dato, Inc.)
    5. Build Applications Quickly Scalably - Carlos Guestrin (Dato, Inc.)
    6. Fundamentals of GraphLab Create - Carlos Guestrin (Dato, Inc.)
    7. Demo: Building an End-to-End Intelligent Application - Carlos Guestrin (Dato, Inc.)
    8. Defining Intelligent Microservices - Carlos Guestrin (Dato, Inc.)
    9. Building Trust in Machine Learning Models - Carlos Guestrin (Dato, Inc.)
    10. Exploring Why a Machine Learning Model Makes a Prediction - Carlos Guestrin (Dato, Inc.)
    11. Dato Machine Learning Platform - Carlos Guestrin (Dato, Inc.)
  2. Deploying Deep Learning at Scale
    1. What is Deep Learning? - Naveen Rao (Nervana)
    2. Deep Learning Model Architectures - Naveen Rao (Nervana)
    3. Automating Human Tasks - Naveen Rao (Nervana)
    4. Challenges in Deep Learning - Naveen Rao (Nervana)
    5. Nervana Compute Topology - Naveen Rao (Nervana)
    6. Nervana Platform, with Neon Deep Learning Framework - Naveen Rao (Nervana)
  3. TensorFlow: Machine Learning for Everyone
    1. Pushing the Boundaries of Machine Learning - Rajat Monga (Google)
    2. What is TensorFlow? - Rajat Monga (Google)
    3. TensorFlow: Under the Hood - Rajat Monga (Google)
    4. Machine Learning in TensorFlow - Rajat Monga (Google)
    5. Updates to TensorFlow - Rajat Monga (Google)
    6. TensorFlow Applications, including Spark - Rajat Monga (Google)
    7. Google Cloud Machine Learning Platform - Rajat Monga (Google)
  4. TensorFlow: Large-scale Analytics and Distributed Machine Learning with TensorFlow, BigQuery, and Dataflow (Apache Beam)
    1. Deep Learning and Distributed Training - Kazunori Sato and Amy Unruhand (Google)
    2. Google Brain, Google Cloud - Kazunori Sato and Amy Unruhand (Google)
    3. Neural Networks in Production - Kazunori Sato and Amy Unruhand (Google)
    4. Demo: Cloud-vision API Explorer - Kazunori Sato and Amy Unruhand (Google)
    5. Demo: Cloud-speech API - Kazunori Sato and Amy Unruhand (Google)
    6. TensorFlow for Deep Learning - Kazunori Sato and Amy Unruhand (Google)
    7. Learning New Image Classes using Apache Beam - Kazunori Sato and Amy Unruhand (Google)
    8. Demo: Using Cloud Datalab - Kazunori Sato and Amy Unruhand (Google)
  5. A Scalable Implementation of Deep Learning on Spark
    1. What is an Artificial Neural Network? - Alexander Ulanov (Hewlett-Packard Labs)
    2. Implementing the Multilayer Perceptron in Spark - Alexander Ulanov (Hewlett-Packard Labs)
    3. Basic Linear Algebra Subprograms (BLAS) - Alexander Ulanov (Hewlett-Packard Labs)
    4. Scalability - Alexander Ulanov (Hewlett-Packard Labs)
    5. Scalability Testing - Alexander Ulanov (Hewlett-Packard Labs)
  6. SparkNet: Training Deep Networks in Spark
    1. Sparknet for Deep Learning - Robert Nishihara (UC Berkeley)
    2. How to Read Data into Neural Nets - Robert Nishihara (UC Berkeley)
    3. How to Use SparkNet - Robert Nishihara (UC Berkeley)
    4. Distributed Training for Neutral Nets - Robert Nishihara (UC Berkeley)
    5. Experiment Using AlexNet - Robert Nishihara (UC Berkeley)
    6. Experiment Using GoogleNet - Robert Nishihara (UC Berkeley)
    7. Parallelization Schemes - Robert Nishihara (UC Berkeley)
    8. SparkNet Code Paper - Robert Nishihara (UC Berkeley)

Product information

  • Title: Up and Running with Deep Learning
  • Author(s): O'Reilly Media, Inc., Shannon Cutt
  • Release date: May 2016
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 9781491963203