by Shams Ul Azeem | Released January 2017 | ISBN: 9781786466440

Tackle common machine learning problems with Google's TensorFlow library and build deployable solutions About This VideoUse raw real-world data to create pipelines to train and apply classifiers using TenserFlowProductionize challenges and solutionsGo through a full lifecycle of a TensorFlow solution with a practical demonstration ofsystem setup, training, validation, and creating pipelines for the real worldIn DetailTensorFlow is an open source software library for numerical computation using data flow graphs. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.This video addresses common commercial machine learning problems using Google's TensorFlow library. It will not only help you discover what TensorFlow is and how to use it, but will also show you the unbelievable things that can be done in machine learning with the help of examples/real-world use cases. We start off with the basic installation of Tensorflow, moving on to covering the unique features of the library such as Data Flow Graphs, training, and visualization of performance with TensorBoard—all within an example-rich context using problems from multiple sources.. The focus is on introducing new concepts through problems that are coded and solved over the course of each section. Show and hide more

1. Chapter 1 : Getting Started with Deep Learning
   • The Course Overview 00:03:48
   • Introducing Deep Learning 00:03:59
   • Installing TensorFlow on Mac OSX 00:03:51
   • Installation on Windows – Pre-Reqeusite Virtual Machine Setup 00:02:49
   • Installation on Windows/Linux 00:04:01
2. Chapter 2 : Your First Classifier
   • The Hand-Written Letters Dataset 00:03:01
   • Automating Data Preparation 00:03:20
   • Understanding Matrix Conversions 00:05:34
   • The Machine Learning Life Cycle 00:01:52
   • Reviewing Outputs and Results 00:02:51
3. Chapter 3 : The TensorFlow Toolbox
   • Getting Started with TensorBoard 00:05:09
   • TensorBoard Events and Histograms 00:05:22
   • The Graph Explorer 00:05:09
   • Our Previous Project on TensorBoard 00:05:02
4. Chapter 4 : Cats and Dogs – Convolutional Neural Networks
   • Fully Connected Neural Networks 00:04:44
   • Convolutional Neural Networks 00:04:59
   • Programming a CNN 00:05:02
   • Using TensorBoard on Our CNN 00:01:58
   • CNN Versus Fully Connected Network Performance 00:02:08
Show and hide more