Book Image

Hands-On Machine Learning on Google Cloud Platform

By : Giuseppe Ciaburro, V Kishore Ayyadevara, Alexis Perrier

Book Image

Hands-On Machine Learning on Google Cloud Platform

By: Giuseppe Ciaburro, V Kishore Ayyadevara, Alexis Perrier

Overview of this book

Google Cloud Machine Learning Engine combines the services of Google Cloud Platform with the power and flexibility of TensorFlow. With this book, you will not only learn to build and train different complexities of machine learning models at scale but also host them in the cloud to make predictions. This book is focused on making the most of the Google Machine Learning Platform for large datasets and complex problems. You will learn from scratch how to create powerful machine learning based applications for a wide variety of problems by leveraging different data services from the Google Cloud Platform. Applications include NLP, Speech to text, Reinforcement learning, Time series, recommender systems, image classification, video content inference and many other. We will implement a wide variety of deep learning use cases and also make extensive use of data related services comprising the Google Cloud Platform ecosystem such as Firebase, Storage APIs, Datalab and so forth. This will enable you to integrate Machine Learning and data processing features into your web and mobile applications. By the end of this book, you will know the main difficulties that you may encounter and get appropriate strategies to overcome these difficulties and build efficient systems.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Introducing the Google Cloud Platform

Introducing the Google Cloud Platform

ML and the cloud

Introducing the GCP

Getting started with GCP

Further reading

Google Compute Engine

Google Compute Engine

Google Compute Engine

Setting up a data science stack on the VM

BOX the ipython console

Resources and further reading

Google Cloud Storage

Google Cloud Storage

Google Cloud Storage

Accessing control lists

Creating a bucket in Google Cloud Storage

Life cycle management

Google Cloud SQL

Querying Your Data with BigQuery

Querying Your Data with BigQuery

Approaching big data

Data structuring

Querying the database

Google BigQuery

Visualizing data with Google Data Studio

Transforming Your Data

Transforming Your Data

How to clean and prepare the data

Finding outliers in the data

Scale of features

Google Cloud Dataflow

Essential Machine Learning

Essential Machine Learning

Applications of machine learning

Supervised and unsupervised machine learning

Overview of machine learning techniques

Google Machine Learning APIs

Google Machine Learning APIs

Cloud Translation API

Natural Language API

Speech-to-text API

Video Intelligence API

Creating ML Applications with Firebase

Creating ML Applications with Firebase

Features of Firebase

Neural Networks with TensorFlow and Keras

Neural Networks with TensorFlow and Keras

Overview of a neural network

Evaluating Results with TensorBoard

Evaluating Results with TensorBoard

Setting up TensorBoard

Overview of summary operations

Optimizing the Model through Hyperparameter Tuning

Optimizing the Model through Hyperparameter Tuning

The intuition of hyperparameter tuning

Preventing Overfitting with Regularization

Preventing Overfitting with Regularization

Intuition of over/under fitting

Beyond Feedforward Networks – CNN and RNN

Beyond Feedforward Networks – CNN and RNN

Convolutional neural networks

Handwriting Recognition using CNN and TensorFlow

Recurrent neural network

Long short-term memory networks

Handwriting Recognition using RNN and TensorFlow

Time Series with LSTMs

Time Series with LSTMs

Introducing time series

Classical approach to time series

Time series models

Removing seasonality from a time series

LSTM for time series analysis

Reinforcement Learning

Reinforcement Learning

Reinforcement learning introduction

Reinforcement learning techniques

Cart-Pole system

Generative Neural Networks

Generative Neural Networks

Unsupervised learning

Generative models

Feature extraction using RBM

Autoencoder with Keras

Chatbots

Chatbots fundamentals

Google Cloud Dialogflow

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Generative Neural Networks

In recent times, neural networks have been used as generative models: algorithms able to replicate the distribution of data in input to then be able to generate new values starting from that distribution. Usually, an image dataset is analyzed, and we try to learn the distribution associated with the pixels of the images to produce shapes similar to the original ones. Much work is ongoing to get neural networks to create novels, articles, art, and music.

Artificial intelligence (AI) researchers are interested in generative models because they represent a springboard towards the construction of AI systems able to use raw data from the world and automatically extract knowledge. These models seem to be a way to train computers to understand the concepts without the need for researchers to teach such concepts a priori. It would be a big step forward compared...