Book Image

Deep Learning for Beginners

By : Dr. Pablo Rivas
Book Image

Deep Learning for Beginners

By: Dr. Pablo Rivas

Overview of this book

With information on the web exponentially increasing, it has become more difficult than ever to navigate through everything to find reliable content that will help you get started with deep learning. This book is designed to help you if you're a beginner looking to work on deep learning and build deep learning models from scratch, and you already have the basic mathematical and programming knowledge required to get started. The book begins with a basic overview of machine learning, guiding you through setting up popular Python frameworks. You will also understand how to prepare data by cleaning and preprocessing it for deep learning, and gradually go on to explore neural networks. A dedicated section will give you insights into the working of neural networks by helping you get hands-on with training single and multiple layers of neurons. Later, you will cover popular neural network architectures such as CNNs, RNNs, AEs, VAEs, and GANs with the help of simple examples, and learn how to build models from scratch. At the end of each chapter, you will find a question and answer section to help you test what you've learned through the course of the book. By the end of this book, you'll be well-versed with deep learning concepts and have the knowledge you need to use specific algorithms with various tools for different tasks.
Table of Contents (20 chapters)
1
Section 1: Getting Up to Speed
8
Section 2: Unsupervised Deep Learning
13
Section 3: Supervised Deep Learning

Identifying overfitting and generalization

Often, when we are in a controlled machine learning setting, we are given a dataset that we can use for training and a different set that we can use for testing. The idea is that you only run the learning algorithm on the training data, but when it comes to seeing how good your model is, you feed your model the test data and observe the output. It is typical for competitions and hackathons to give out the test data but withhold the labels associated with it because the winner will be selected based on how well the model performs on the test data and you don't want them to cheat by looking at the labels of the test data and making adjustments. If this is the case, we can use a validation dataset, which we can create by ourselves by separating a portion of the training data to be the validation data.

The whole point of having separate sets, namely a validation or test dataset, is to measure the performance on this data, knowing that our model...