Book Image

Applied Deep Learning with Keras

By : Ritesh Bhagwat, Mahla Abdolahnejad, Matthew Moocarme
5 (1)
Book Image

Applied Deep Learning with Keras

5 (1)
By: Ritesh Bhagwat, Mahla Abdolahnejad, Matthew Moocarme

Overview of this book

Though designing neural networks is a sought-after skill, it is not easy to master. With Keras, you can apply complex machine learning algorithms with minimum code. Applied Deep Learning with Keras starts by taking you through the basics of machine learning and Python all the way to gaining an in-depth understanding of applying Keras to develop efficient deep learning solutions. To help you grasp the difference between machine and deep learning, the book guides you on how to build a logistic regression model, first with scikit-learn and then with Keras. You will delve into Keras and its many models by creating prediction models for various real-world scenarios, such as disease prediction and customer churning. You’ll gain knowledge on how to evaluate, optimize, and improve your models to achieve maximum information. Next, you’ll learn to evaluate your model by cross-validating it using Keras Wrapper and scikit-learn. Following this, you’ll proceed to understand how to apply L1, L2, and dropout regularization techniques to improve the accuracy of your model. To help maintain accuracy, you’ll get to grips with applying techniques including null accuracy, precision, and AUC-ROC score techniques for fine tuning your model. By the end of this book, you will have the skills you need to use Keras when building high-level deep neural networks.
Table of Contents (12 chapters)
Applied Deep Learning with Keras
Preface
Preface

Cross-Validation


Resampling techniques are an important group of techniques in statistical data analysis. They involve repeatedly drawing samples from a dataset to create the training set and the test set. At each repetition, they fit and evaluate the model using the samples drawn from the dataset for the training set and the test set at that repetition. Using these techniques can provide us with information about the model that is otherwise not obtainable by fitting and evaluating the model only once using one training set and one test set. Since resampling methods involve fitting a model to the training data several times, they are computationally expensive. Therefore, when it comes to deep learning, we only implement them in the cases where the dataset and the network are relatively small and the available computational power allows us to do so.

In this section, you will learn about a very important resampling method called cross-validation. Cross-validation is one of the most important...