Book Image

Machine Learning Using TensorFlow Cookbook

By : Luca Massaron, Alexia Audevart, Konrad Banachewicz
Book Image

Machine Learning Using TensorFlow Cookbook

By: Luca Massaron, Alexia Audevart, Konrad Banachewicz

Overview of this book

The independent recipes in Machine Learning Using TensorFlow Cookbook will teach you how to perform complex data computations and gain valuable insights into your data. Dive into recipes on training models, model evaluation, sentiment analysis, regression analysis, artificial neural networks, and deep learning - each using Google’s machine learning library, TensorFlow. This cookbook covers the fundamentals of the TensorFlow library, including variables, matrices, and various data sources. You’ll discover real-world implementations of Keras and TensorFlow and learn how to use estimators to train linear models and boosted trees, both for classification and regression. Explore the practical applications of a variety of deep learning architectures, such as recurrent neural networks and Transformers, and see how they can be used to solve computer vision and natural language processing (NLP) problems. With the help of this book, you will be proficient in using TensorFlow, understand deep learning from the basics, and be able to implement machine learning algorithms in real-world scenarios.
Table of Contents (15 chapters)
5
Boosted Trees
11
Reinforcement Learning with TensorFlow and TF-Agents
13
Other Books You May Enjoy
14
Index

Running a test on a difficult problem

Throughout the chapter, we have provided recipes to handle tabular data in a successful way. Each recipe is not actually a solution in itself, but a piece of a puzzle. When the pieces are combined you can get excellent results and in this last recipe, we will demonstrate how to assemble all the recipes together to successfully complete a difficult Kaggle challenge.

The Kaggle competition, Amazon.com – Employee Access Challenge (https://www.kaggle.com/c/amazon-employee-access-challenge), is a competition that's notable for the high-cardinality variables involved and is a solid benchmark that's used to compare gradient boosting algorithms. The aim of the competition is to develop a model that can predict whether an Amazon employee should be given access to a specific resource based on their role and activities. The answer should be given as likelihood. As predictors, you have different ID codes corresponding to the type of resource...