English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 1h 40m | 348 MB
Develop fast, efficient distributed deep learning models with Apache Spark
Deep Learning is a subset of Machine Learning whereby datasets with several layers of complexity can be processed efficiently. This tutorial brings together two of the most popular buzzwords of today—big data and Artificial Intelligence—by showing you how you can implement Deep Learning solutions using the power of Apache Spark.
The tutorial begins by explaining the fundamentals of Apache Spark and deep learning. You will set up a Spark environment to perform deep learning and learn about the different types of neural net and the principles of distributed modeling (model- and data-parallelism, and more). You will then implement deep learning models (such as CNN, RNN, LTSMs) on Spark, acquire hands-on experience of what it takes, and get a general feeling for the complexity we are dealing with. You will also see how you can use libraries such as Deeplearning4j to perform deep learning on a distributed CPU and GPU setup.
By the end of this course, you’ll have gained experience by implementing models for applications such as object recognition, text analysis, and voice recognition. You will even have designed human expert games.
This is a step-by-step and fast-paced guide that will help you learn how to create a ML model using the Apache Spark ML toolkit. With this practical approach, you will take your skills to the next level and will be able to create ML pipelines effectively.
What You Will Learn
- Get to know basic Apache Spark and deep learning concepts
- Explore deep learning neural networks such as RBM, RNN, and DBN using some of the most popular industrial deep learning frameworks
- Learn how to leverage big data to solve real-world problems using deep learning
- Understand how to formulate real-world prediction problems as machine learning tasks, how to choose the right neural net architecture for a problem, and how to train neural nets using DL4J
- Get up-and-running and gain an insight into the deep learning library DL4J and its practical uses
- Design successful solutions with Extreme Learning machines
- Train and test neural networks to fit your data model
Table of Contents
The Fundamentals of Apache Spark and Deep Learning
1 The Course Overview
2 Review of Key Machine Learning Terminology and Fundamentals
3 Fundamentals of Deep Networks Feature Engineering
4 The Building Blocks of Deep Learning
5 Learning Path for Deep Learning
6 Deep Learning Use Cases
Up and Running with the Spark Environment for Performing Deep Learning
7 Pre-requisites and Installation
8 Up and Running with DL4J on Spark
9 Configuration and Test Run
10 Up and Running with TensorFlow on Spark from Yahoo
Hands-On with the DL4J Ecosystem
11 Understanding the Basics of Deep Learning
12 ND4J for NumPy-like Arrays and Operations
13 Data.Vec for Data Preparation Pipelines
14 DL4J for Building Neural Network Architectures
GPU Distributed Training and CNN
15 Understanding the Basics of GPU
16 Parallel Training with Multiple GPUs
17 Designing a Basic CNN
18 Implement a Basic CNN on DL4J in Spark
Recurrent Neural Networks (RNN) and LSTMs
19 Basics and Design of RNN
20 Implement a Basic RNN on DL4J in Spark
21 Design a Basic LSTM
22 Implement a Basic LSTM in Spark
Resolve the captcha to access the links!