Book Image

The TensorFlow Workshop

By : Matthew Moocarme, Abhranshu Bagchi, Anthony So, Anthony Maddalone
Book Image

The TensorFlow Workshop

By: Matthew Moocarme, Abhranshu Bagchi, Anthony So, Anthony Maddalone

Overview of this book

Getting to grips with tensors, deep learning, and neural networks can be intimidating and confusing for anyone, no matter their experience level. The breadth of information out there, often written at a very high level and aimed at advanced practitioners, can make getting started even more challenging. If this sounds familiar to you, The TensorFlow Workshop is here to help. Combining clear explanations, realistic examples, and plenty of hands-on practice, it’ll quickly get you up and running. You’ll start off with the basics – learning how to load data into TensorFlow, perform tensor operations, and utilize common optimizers and activation functions. As you progress, you’ll experiment with different TensorFlow development tools, including TensorBoard, TensorFlow Hub, and Google Colab, before moving on to solve regression and classification problems with sequential models. Building on this solid foundation, you’ll learn how to tune models and work with different types of neural network, getting hands-on with real-world deep learning applications such as text encoding, temperature forecasting, image augmentation, and audio processing. By the end of this deep learning book, you’ll have the skills, knowledge, and confidence to tackle your own ambitious deep learning projects with TensorFlow.
Table of Contents (13 chapters)
Preface

Summary

In this chapter, you began your journey into creating ANNs in TensorFlow. You saw how simple it is to create regression and classification models by utilizing Keras layers. Keras layers are distinct classes that exist in a separate library that uses TensorFlow in the backend. Due to their popularity and ease of use, they are now included in TensorFlow and can be called in the same way as any other TensorFlow class.

You created ANNs with fully connected layers, varying layers, beginning with an ANN that resembles a linear regression algorithm, which is equivalent to a single-layer ANN. Then, you added layers to your ANN and added activation functions to the output of the layers. Activation functions can be used to determine whether a unit is fired or can be used to bind the value of the output from a given unit. Regression models aim to predict a continuous variable from the data provided. In the exercises and activities throughout this chapter, you attempted to predict...