Apache Spark Deep Learning Advanced Recipes

Apache Spark Deep Learning Advanced Recipes

English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 1h 35m | 624 MB

Implement practical hands-on examples with Apache Spark

In this video course, you’ll work through specific recipes to generate outcomes for deep learning algorithms—without getting bogged down in theory. From using LSTMs in generative networks to creating a movie recommendation engine, this course tackles both common and not so common problems so you can perform deep learning in a distributed environment.
In addition, you’ll get access to deep learning code within Spark that you can reuse to answer similar problems or tweak to answer slightly different problems. You’ll learn how to predict real estate value using XGBoost. You’ll also explore how to create a movie recommendation engine using popular libraries such as TensorFlow and Keras. By the end of the course, you’ll have the expertise to train and deploy efficient deep learning models on Apache Spark.

This course includes practical, easy-to-understand solutions on how you can implement the popular deep learning libraries such as TensorFlow and Keras to train your deep learning models on Apache Spark.

What You Will Learn

  • Organize dataframes for deep learning evaluation
  • Apply testing and training modeling to ensure accuracy
  • Access readily available code that may be reusable
  • Plot and visualize the images
  • Train the LSTM model
  • Manipulate and merge the MovieLens datasets
Table of Contents

Using LSTMs in Generative Networks
1 The Course overview
2 Downloading Novels Books that will be used as Input Text
3 Preparing and Cleansing Data
4 Tokenizing Sentences
5 Training and Saving the LSTM Model
6 Generating Similar Text using the Model

Real Estate Value Prediction Using XGBoost
7 Downloading the King County House Sales Dataset
8 Performing Exploratory Analysis and Visualization
9 Plotting Correlation Between Price and Other Features
10 Predicting the Price of a House

Face Recognition Using Deep Convolutional Networks
11 Downloading and Loading the MIT-CBCL Dataset into the Memory
12 Plotting and Visualizing Images from the Directory
13 Preprocessing Images

Creating and Visualizing Word Vectors Using Word2Vec
14 Acquiring Data
15 Importing the Necessary Libraries
16 Preparing the Data
17 Building and Training the Model
18 Visualizing Further
19 Analyzing Further

Creating a Movie Recommendation Engine with Keras
20 Downloading MovieLens Datasets
21 Manipulating and Merging the MovieLens Datasets
22 Exploring the MovieLens Datasets
23 Preparing Dataset for the Deep Learning Pipeline
24 Applying the Deep Learning Model with Keras