Book Image

Hands-On Neural Networks

By : Leonardo De Marchi, Laura Mitchell
Book Image

Hands-On Neural Networks

By: Leonardo De Marchi, Laura Mitchell

Overview of this book

Neural networks play a very important role in deep learning and artificial intelligence (AI), with applications in a wide variety of domains, right from medical diagnosis, to financial forecasting, and even machine diagnostics. Hands-On Neural Networks is designed to guide you through learning about neural networks in a practical way. The book will get you started by giving you a brief introduction to perceptron networks. You will then gain insights into machine learning and also understand what the future of AI could look like. Next, you will study how embeddings can be used to process textual data and the role of long short-term memory networks (LSTMs) in helping you solve common natural language processing (NLP) problems. The later chapters will demonstrate how you can implement advanced concepts including transfer learning, generative adversarial networks (GANs), autoencoders, and reinforcement learning. Finally, you can look forward to further content on the latest advancements in the field of neural networks. By the end of this book, you will have the skills you need to build, train, and optimize your own neural network model that can be used to provide predictable solutions.
Table of Contents (16 chapters)
Free Chapter
1
Section 1: Getting Started
4
Section 2: Deep Learning Applications
9
Section 3: Advanced Applications

Understanding word embeddings

Embedding is a mathematical structure contained within another instance. If we are embedding an object X in an object Y, we will be preserving the structure of the objects and so the instance.

Word embedding is a technique to map words to vectors, creating a multidimensional space that will allow the creation of similar representations for similar words. Each word is represented by a single vector with often tens or hundreds of dimensions, in contrast to other representations such as one-hot encoding that can have thousands or even millions of dimensions.

When we have words in the form of vectors, we end up using all mathematical techniques that we would on pure numbers. Also when transformed into vectors, words will keep the same proprieties that numbers have.

It also means that we could start doing operations as follows:

King - man + woman =queen...