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

DBN architecture

A DBN is a multilayer belief network where each layer is an RBM stacked against one another. Apart from the first and final layers of the DBN, each layer serves as both a hidden layer to the nodes before it, and as the input layer to the nodes that come after it:

Two layers in the DBN are connected by a matrix of weights. The top two layers of a DBN are undirected, which gives a symmetric connection between them, forming an associative memory. The lower two layers have directed connections from the layers above. The presence of direction converts associative memory into observed variables:

The two most significant properties of DBNs are as follows:

  • A DBN learns top-down, generative weights via an efficient, layer by layer procedure. These weights determine how the variables in one layer depend on the layer above.
  • Once training is complete, the values of the...