A Tutorial on Deep Neural Networks for Intelligent Systems

TL;DR

This tutorial provides an overview of deep neural networks, including their origins, core components like Restricted Boltzmann Machines, and practical applications such as digit recognition and speech processing.

Contribution

It offers a comprehensive introduction to DNNs, detailing their structure, training methods, and applications, serving as a foundational resource for understanding deep learning in intelligent systems.

Findings

Demonstrates DNNs' effectiveness in pattern recognition tasks.

Explains the architecture and training of Restricted Boltzmann Machines and Deep Belief Networks.

Provides practical examples with MNIST and speech recognition applications.

Abstract

Developing Intelligent Systems involves artificial intelligence approaches including artificial neural networks. Here, we present a tutorial of Deep Neural Networks (DNNs), and some insights about the origin of the term "deep"; references to deep learning are also given. Restricted Boltzmann Machines, which are the core of DNNs, are discussed in detail. An example of a simple two-layer network, performing unsupervised learning for unlabeled data, is shown. Deep Belief Networks (DBNs), which are used to build networks with more than two layers, are also described. Moreover, examples for supervised learning with DNNs performing simple prediction and classification tasks, are presented and explained. This tutorial includes two intelligent pattern recognition applications: hand- written digits (benchmark known as MNIST) and speech recognition.