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
Section 1: Getting Started
Section 2: Deep Learning Applications
Section 3: Advanced Applications

Convolutional layers

Convolution is a typical operation in signal processing that expresses how two functions modify each other and create a third function. Convolution layers are actually implementing an autocorrelation operation, but in practice for our case convolution and autocorrelation are the same, as they can be interchanged with a simple rotation operation.

Let's call our input x, the set of weights it passes through w, the output signal s, and the time t. We want to give more importance to inputs that are more recent, therefore we will use the function w(a) to define the weights, where a is the age of the measurement. The convolutional operation is the process of combining the signal s and the set of weights, which is also called a kernel. As we are dealing with data from real applications and not just match abstractions, the time must be discrete. In mathematical...