book

Machine Learning Using TensorFlow Cookbook

Name: Machine Learning Using TensorFlow Cookbook
ISBN: 9781800208865

by Alexia Audevart, Konrad Banachewicz, Luca Massaron

February 2021

Intermediate to advanced

416 pages

9h 25m

English

Packt Publishing

Read now

Unlock full access

Preface
Who this book is forWhat this book coversTo get the most out of this book Get in touch
Getting Started with TensorFlow 2.x
How TensorFlow worksGetting readyHow to do it…How it works…See alsoDeclaring variables and tensorsGetting readyHow to do it…How it works…There's more…Using eager executionGetting readyHow to do it…How it works…There's more…Working with matricesGetting readyHow to do it…How it works…See alsoDeclaring operationsGetting readyHow to do it…How it works…There's more…Implementing activation functionsGetting readyHow to do it…How it works…There's more…Working with data sourcesGetting readyHow to do it…How it works…See alsoAdditional resourcesGetting readyHow to do it…
The TensorFlow Way
Operations using eager executionGetting readyHow to do it...How it works...Layering nested operationsGetting readyHow to do it...How it works...There's more...Working with multiple layersGetting readyHow to do it...How it works...Implementing loss functionsGetting readyHow to do it...How it works...There's more...Implementing backpropagationGetting readyHow to do it...How it works...There's more...See alsoWorking with batch and stochastic trainingGetting readyHow to do it...How it works...There's more...Combining everything togetherGetting readyHow to do it...How it works...There's more...See also
Keras
Introduction Understanding Keras layersGetting ready How to do it... How it works... See alsoUsing the Keras Sequential APIGetting readyHow to do it... How it works... See also Using the Keras Functional APIGetting ready How to do it... Creating a Functional modelUsing callable models like layersCreating a model with multiple inputs and outputsShared layers Extracting and reusing nodes in the graph of layers How it works... There's more...See alsoUsing the Keras Subclassing APIGetting ready How to do it... Creating a custom layerCreating a custom modelHow it works... See alsoUsing the Keras Preprocessing APIGetting ready How to do it... Sequence preprocessingText preprocessingImage preprocessingHow it works... See also
Linear Regression
Learning the TensorFlow way of linear regressionGetting readyHow to do it...How it works...There's more...Turning a Keras model into an EstimatorGetting readyHow to do it...How it works...There's more...Understanding loss functions in linear regressionGetting readyHow to do it...How it works...There's more...Implementing Lasso and Ridge regressionGetting readyHow to do it...How it works...There's more...Implementing logistic regressionGetting readyHow to do it...How it works...There's more...Resorting to non-linear solutionsGetting readyHow to do it...How it works...There's more...Using Wide & Deep modelsGetting readyHow to do it...How it works...
Boosted Trees
IntroductionHow to do it...How it works...See also
Neural Networks
Implementing operational gatesGetting readyHow to do it...How it works...Working with gates and activation functionsGetting readyHow to do it...How it works...There's more...Implementing a one-layer neural networkGetting readyHow to do it...How it works...Implementing different layersGetting readyHow to do it...How it works...Using a multilayer neural networkGetting readyHow to do it...How it works...Improving the predictions of linear modelsGetting readyHow to do it...How it works...Learning to play Tic-Tac-ToeGetting readyHow to do it...How it works...
Predicting with Tabular Data
Processing numerical dataGetting readyHow to do it…How it works…There's more…Processing datesGetting readyHow to do it…How it works…There's more…Processing categorical dataGetting readyHow to do it…How it works…There's more…Processing ordinal dataGetting readyHow to do it…How it works…Processing high-cardinality categorical dataGetting readyHow to do it…How it works…There's more…Wrapping up all the processingGetting readyHow to do it…How it works…There's more…Setting up a data generatorGetting readyHow to do it…How it works…Creating custom activations for tabular dataGetting readyHow to do it…How it works…Running a test on a difficult problemGetting readyHow to do it…How it works…
Convolutional Neural Networks
IntroductionImplementing a simple CNNGetting readyHow to do it...How it works...There's more...See alsoImplementing an advanced CNNGetting readyHow to do it...How it works...See alsoRetraining existing CNN modelsGetting readyHow to do it... How it works...See alsoApplying StyleNet and the neural style projectGetting readyHow to do it...How it works...See alsoImplementing DeepDreamGetting readyHow to do it...There's more...See also
Recurrent Neural Networks
Text generationHow to do it...See alsoSentiment classificationHow to do it...See alsoStock price predictionHow to do it...Open-domain question answeringHow to do it...Summary

Transformers
Text generationHow do we go about it?Output:Output:Output:See alsoSentiment analysisHow do we go about it?See alsoOpen-domain question answeringHow do we go about it?
Reinforcement Learning with TensorFlow and TF-Agents
GridWorldHow do we go about it?See alsoCartPoleHow do we go about it?See alsoMABHow do we go about it?See also
Taking TensorFlow to Production
Visualizing Graphs in TensorBoardGetting readyHow to do it...How it works...See alsoThere's more...Managing Hyperparameter tuning with TensorBoard's HParamsGetting readyHow to do it...See also Implementing unit testsGetting readyHow to do it...How it works...See also Using multiple executorsGetting readyHow to do it...How it works...There's more...Parallelizing TensorFlowGetting readyHow to do it...How it works...See also There's more...Saving and restoring a TensorFlow modelGetting readyHow to do it...How it works...See also Using TensorFlow ServingGetting readyHow to do it...How it works...There's more...
Other Books You May Enjoy
Index

Content preview from Machine Learning Using TensorFlow Cookbook

5 Boosted Trees

In this chapter, we describe boosted trees: the TensorFlow (TF) approach to gradient boosting. It is a class of ML algorithms that produce a prediction model in the form of an ensemble of weak prediction models, typically decision trees. The model is constructed in a stage-wise fashion and generalized by utilizing an arbitrary (differentiable) loss function. Gradient boosted trees are an extremely popular class of algorithms, as they can be parallelized (at the tree construction stage), can natively handle missing values and outliers, and require minimal data preprocessing.

Introduction

In this chapter, we briefly demonstrate how to approach a binary classification problem using BoostedTreesClassifier. We will apply the technique ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Automated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python

Publisher Resources

ISBN: 9781800208865

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Machine Learning Using TensorFlow Cookbook

by Alexia Audevart, Konrad Banachewicz, Luca Massaron

5

Boosted Trees

Introduction

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.