O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Mastering Deep Learning using Apache Spark

Video Description

Design deep learning models to edge industrial-grade apps

About This Video

  • Create robust deep learning pipelines that leverage Apache Spark for fast execution
  • Perform advanced classification of non-structured data using Deep Learning (DL) techniques
  • Adapt the Neural Network configuration and decide when to add the next layer to achieve the results needed

In Detail

Deep learning has solved tons of interesting real-world problems in recent years. Apache Spark has emerged as the most important and promising machine learning tool and currently a stronger challenger of the Hadoop ecosystem. In this course, you’ll learn about the major branches of AI and get familiar with several core models of Deep Learning in its natural way.

You’ll begin with building deep learning networks to deal with speech data and explore tricks to solve NLP problems and classify video frames using RNN and LSTMs. You’ll also learn to implement the anomaly detection model that leverages reinforcement learning techniques to improve cyber security.

Moving on, you’ll explore some more advanced topics by performing prediction classification on image data using the GAN encoder and decoder. Then you’ll configure Spark to use multiple workers and CPUs to distribute your Neural Network training. Finally, you’ll track progress, solve the most common problems in your neural network, and debug your models that run within the distributed Spark engine.

Downloading the example code for this course: You can download the example code files for all Packt video courses you have purchased from your account at http://www.PacktPub.com. If you purchased this course elsewhere, you can visit http://www.PacktPub.com/support and register to have the files e-mailed directly to you.

Table of Contents

  1. Chapter 1 : Convolutional Neural Networks for Speech Recognition (NLP)
    1. The Course Overview 00:02:20
    2. Analyzing Input Text Data That Will Need to Be Classified 00:03:31
    3. Configuring Word Vectors That Will Be Used in Our Network 00:03:56
    4. Adding Layers to Deep Neural Network 00:03:54
    5. Asserting Classification of Input Sentences 00:04:08
  2. Chapter 2 : Performing Video Classification Using RNN and LSTMs
    1. Generating Input Video Data 00:04:48
    2. Creating a Neural Network for Video Classification 00:03:56
    3. Adding RNN and LSTMs to Network to Perform a Task Better 00:04:18
    4. Testing and Validating Deep Learning Model 00:05:39
  3. Chapter 3 : Transfer Learning and Pre-Trained Models
    1. Creating Paragraph Vectors 00:02:36
    2. Adding Labels to Non-Labelled Data 00:04:10
    3. Finding Similarity between Vectors 00:03:59
    4. Creating a Model That Can Guess the Meaning of The Word 00:03:24
  4. Chapter 4 : Deep Reinforcement Learning
    1. Anomaly Detection Problem Explained 00:04:15
    2. Extracting Features from Input Data Using Multi-Layer Approach 00:05:25
    3. Adding Layer That Finds an Actual Anomaly 00:04:28
    4. Testing and Validating Results from Our Deep Learning Model 00:05:33
  5. Chapter 5 : Generative Adversarial Networks
    1. Creating Data Generator for GAN 00:03:34
    2. Adding Discriminator for Our Data 00:06:07
    3. Create Classifier for Generated Data 00:04:55
    4. Performing Validation of Our Model 00:04:27
  6. Chapter 6 : Distributed Models
    1. Configuring Spark for High Data Distribution 00:05:12
    2. Fetching Input Set into Distributed Data Set Using Spark API 00:04:26
    3. Creating Training Master That Supervise Computations on the Workers 00:04:55
    4. Evaluating Speed of Distributed Training Using Spark 00:03:03
  7. Chapter 7 : Troubleshooting
    1. Monitoring of Models Using Spark UI 00:04:30
    2. Speeding Up Computations by Employing Caching 00:03:49
    3. Partitioning Deep Learning Data into Several Workers 00:03:54
    4. Tweaking Spark Workers Configuration 00:04:19