Artificial Neural Networks with Tensorflow 2: Ann Architecture Machine Learning Projects

ISBN-13: 9781484261491 / Angielski / Miękka / 2020 / 726 str.

Poornachandra Sarang

Spis treści

Chapter 1: TensorFlow

Introduction  

What's new in TensorFlow 2

Chapter 2: A Quick Start on TensorFlow  

Hello World for TensorFlow using Google Colab    

Chapter 3: TensorFlow Keras Integration  

tf.keras

Image Classification    

Chapter 4: TensorFlow Hub  

Transfer Learning 

TensorFlow Hub and Keras    

Chapter 5: Regression  

Predicting Continuous Value Output    

Chapter 6: Estimators  

Solving Classification Problems Using Estimators    

Chapter 7: Distributed Training  

Describing tf.distribute.Strategy    

Chapter 8: Text   

Text Classification

Generation with RNN    

Chapter 9: Language Translation  

The seq2seq model for language translation    

Chapter 10: Language Understanding  

Using Transformer Model    

Chapter 11: Image Captioning 

 Attention-based model for captioning images    

Chapter 12: Time Series Forecasting  

Using RNNs

Forecasting a univariate/multivariate time series    

Chapter 13: Style Transfer  

Composing an image in the style of another image    

Chapter 14: Image Generation using GAN  

Introduction to GAN

Generating images using a DCGAN    

Chapter 15: Image Translation  

Colorizing B&W images  

O autorze

Poornachandra Sarang has 30+ years of IT experience and is an experienced author. His work has always focused on state-of-the-art and emerging technologies. He has provided consulting services to—Sun Microsystems, Microsoft, Oracle, and Hewlett-Packard.  He has been a Ph.D. advisor for Computer Science and is currently on a Thesis Advisory Committee for students pursuing Ph.D. in Computer Engineering—setting the course curriculum for both under-graduate and post-graduate courses in Computer Science/Engineering. He has delivered seminars, written articles, and provided consulting recently on Machine Learning and Deep Learning. He maintains a machine learning blog at education.abcom.com.

Blurb

Develop machine learning models across various domains. This book offers a single source that provides comprehensive coverage of the capabilities of TensorFlow 2 through the use of realistic, scenario-based projects.

After learning what's new in TensorFlow 2, you'll dive right into developing machine learning models through applicable projects. This book covers a wide variety of ANN architectures—starting from working with a simple sequential network to advanced CNN, RNN, LSTM, DCGAN, and so on. A full chapter is devoted to each kind of network and each chapter consists of a full project describing the network architecture used, the theory behind that architecture, what data set is used, the pre-processing of data, model training, testing and performance optimizations, and analysis. 

This practical approach can either be used from the beginning through to the end or, if you're already familiar with basic ML models, you can dive right into the application that interests you. Line-by-line explanations on major code segments help to fill in the details as you work and the entire project source is available to you online for learning and further experimentation. With Artificial Neural Networks with TensorFlow 2 you'll see just how wide the range of TensorFlow's capabilities are. 

You will:

• Develop Machine Learning Applications
• Translate languages using neural networks
• Compose images with style transfer