TensorFlow 1.X Recipes for Supervised and Unsupervised Learning

TensorFlow 1.X Recipes for Supervised and Unsupervised Learning

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 3h 19m | 780 MB

Perform Advanced Machine Learning with TensorFlow with 19 hands-on recipes

Deep Learning models often perform significantly better than traditional machine learning algorithms in many tasks. This course consists of hands-on recipes to use deep learning in the context of supervised and unsupervised learning tasks.

After covering the basics of working with TensorFlow, it shows you how to perform the traditional machine learning tasks in supervised learning: regression and classification. This course also covers how to perform unsupervised learning using cutting-edge techniques from Deep Learning.

To address many different use cases, this product presents recipes for both the low-level API (TensorFlow core) as well as the high-level APIs (tf.contrib.lean and Keras).

The course takes a recipe-based approach and will show you how to perform traditional machine learning tasks in supervised learning and also covers how to perform unsupervised learning using cutting-edge techniques from Deep Learning.

What You Will Learn

  • Define and work with the main objects in the TensorFlow library
  • Understand the basic workflow of building models and implement TensorFlow programs
  • Build Deep Learning models and use them to solve real problems
  • Gain practice using both the low-level and the high-level APIs of TensorFlow and understand which one is better for your project
  • Boost the performance of the traditional supervised and unsupervised machine learning models with the use of Deep Learning
Table of Contents

TensorFlow Basics
1 The Course Overview
2 Set Up and Installing TensorFlow
3 Defining and Running a Computational Graph
4 Visualizing a Computational Graph With TensorBoard
5 How to Read Data From Files
6 The Hello World of Deep Learning – Your First Deep Neural Network

Supervised Learning With Deep Neural Networks
7 Building DNN Models for Regression With TensorFlow Core
8 Building DNN Models for Classification With TensorFlow Core
9 Performing Regularization in DNN Models
10 How to Work With Optimizers

Working with High-Level APIs
11 How to Use Keras for Building DNN
12 Performing Regression with Estimators API
13 Performing Classification with Estimators
14 Working with Other Models from Estimators API
15 Customizing DNN Models – Layers, Activations, Optimizers and Metrics

Unsupervised Learning with Deep Neural Networks
16 Building Autoencoders
17 How to Perform PCA for Dimensionality Reduction
18 Building a Restricted Boltzmann Machine
19 How to Perform Clustering