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

TensorFlow for Machine Learning Solutions

Video Description

Explore machine learning concepts using the latest numerical computing library – TensorFlow

About This Video

  • Your quick guide to implementing TensorFlow in your day-to-day machine learning activities
  • Learn advanced techniques that bring more accuracy and speed to machine learning
  • Upgrade your knowledge to the second generation of machine learning with this guide on TensorFlow

In Detail

TensorFlow is an open source software library for Machine Intelligence. The independent solutions in this video course will teach you how to use TensorFlow for complex data computations and will let you dig deeper and gain more insights into your data than ever before. You’ll work through solutions on training models, model evaluation and sentiment analysis – each using Google’s machine learning library TensorFlow.This guide starts with the fundamentals of the TensorFlow library which includes variables, matrices, and various data sources. Moving ahead, you will get hands-on experience with Linear Regression techniques with TensorFlow

Table of Contents

  1. Chapter 1 : Getting Started with TensorFlow
    1. The Course Overview 00:02:02
    2. How TensorFlow Works? 00:03:56
    3. Declaring Tensors 00:02:58
    4. Using Placeholders 00:01:24
    5. Working with Matrices 00:02:13
    6. Declaring Operations 00:02:47
    7. Implementing Activation Functions 00:04:07
    8. Working with Data Sources 00:05:00
  2. Chapter 2 : The TensorFlow Way
    1. Operations in a Computational Graph 00:01:42
    2. Layering Nested Operations 00:01:36
    3. Working with Multiple Layers 00:03:23
    4. Implementing Loss Functions 00:04:38
    5. Implementing Back Propagation 00:04:01
    6. Working with Batch and Stochastic Training 00:03:44
    7. Combining Everything Together 00:02:30
    8. Evaluating Models 00:04:07
  3. Chapter 3 : Linear Regression
    1. Using the Matrix Inverse Method 00:02:13
    2. Implementing a Decomposition Method 00:01:28
    3. Learning the TensorFlow Way of Linear Regression 00:02:19
    4. Understanding Loss Functions in Linear Regression 00:03:02
    5. Implementing Deming regression 00:01:59
    6. Implementing Lasso and Ridge Regression 00:02:25
    7. Implementing Elastic Net Regression 00:02:49
  4. Chapter 4 : Support Vector Machines
    1. Working with a Linear SVM 00:04:35
    2. Reduction to Linear Regression 00:01:36
    3. Working with Kernels in TensorFlow 00:02:37
    4. Implementing a Non-Linear SVM 00:02:17
    5. Implementing a Multi-Class SVM 00:04:05
  5. Chapter 5 : Nearest Neighbor Methods
    1. Working with Nearest Neighbors 00:03:12
    2. Working with Text-Based Distances 00:03:14
    3. Computing with Mixed Distance Functions 00:03:18
    4. Using an Address Matching Example 00:02:59
    5. Using Nearest Neighbors for Image Recognition 00:03:35