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

Understanding Keras layers

Keras layers are the fundamental building blocks of Keras models. Each layer receives data as input, does a specific task, and returns an output.

Keras includes a wide range of built-in layers:

  • Core layers: Dense, Activation, Flatten, Input, Reshape, Permute, RepeatVector, SpatialDropOut, and many more.
  • Convolutional layers for Convolutional Neural Networks: Conv1D, Conv2D, SeparableConv1D, Conv3D, Cropping2D, and many more.
  • Pooling layers that perform a downsampling operation to reduce feature maps: MaxPooling1D, AveragePooling2D, and GlobalAveragePooling3D.
  • Recurrent layers for recurrent neural networks to process recurrent or sequence data: RNN, SimpleRNN, GRU, LSTM, ConvLSTM2D, etc.
  • The embedding layer, only used as the first layer in a model and turns positive integers into dense vectors of fixed size.
  • Merge layers: Add, Subtract, Multiply, Average, Maximum, Minimum, and many more.
  • Advanced activation...