Skip to main content

Über dieses Buch

Discover the potential applications, challenges, and opportunities of deep learning from a business perspective with technical examples. These applications include image recognition, segmentation and annotation, video processing and annotation, voice recognition, intelligent personal assistants, automated translation, and autonomous vehicles.
An Introduction to Deep Learning Business Applications for Developers covers some common DL algorithms such as content-based recommendation algorithms and natural language processing. You’ll explore examples, such as video prediction with fully convolutional neural networks (FCNN) and residual neural networks (ResNets). You will also see applications of DL for controlling robotics, exploring the DeepQ learning algorithm with Monte Carlo Tree search (used to beat humans in the game of Go), and modeling for financial risk assessment. There will also be mention of the powerful set of algorithms called Generative Adversarial Neural networks (GANs) that can be applied for image colorization, image completion, and style transfer.
After reading this book you will have an overview of the exciting field of deep neural networks and an understanding of most of the major applications of deep learning. The book contains some coding examples, tricks, and insights on how to train deep learning models using the Keras framework.
What You Will Learn
Find out about deep learning and why it is so powerful
Work with the major algorithms available to train deep learning models
See the major breakthroughs in terms of applications of deep learning
Run simple examples with a selection of deep learning libraries
Discover the areas of impact of deep learning in business

Who This Book Is For Data scientists, entrepreneurs, and business developers.



Background and Fundamentals


Chapter 1. Introduction

This chapter will describe what the book is about, the book’s goals and audience, why artificial intelligence (AI) is important, and how the topic will be tackled.
Armando Vieira, Bernardete Ribeiro

Chapter 2. Deep Learning: An Overview

Artificial neural networks are not new; they have been around for about 50 years and got some practical recognition after the mid-1980s with the introduction of a method (backpropagation) that allowed for the training of multiple-layer neural networks. However, the true birth of deep learning may be traced to the year 2006, when Geoffrey Hinton [GR06] presented an algorithm to efficiently train deep neural networks in an unsupervised way—in other words, data without labels. They were called deep belief networks (DBNs) and consisted of staked restrictive Boltzmann machines (RBMs), with each one placed on the top of another. DBNs differ from previous networks since they are generative models capable of learning the statistical properties of data being presented without any supervision.
Armando Vieira, Bernardete Ribeiro

Chapter 3. Deep Neural Network Models

The concept of deep learning originated from artificial neural networks research, in which feed-forward neural networks or multilayer perceptrons (MLPs) with many hidden layers are often referred as deep neural networks (DNNs).
Armando Vieira, Bernardete Ribeiro

Deep Learning: Core Applications


Chapter 4. Image Processing

This chapter will describe what the book is about, the book’s goals and audience, why artificial intelligence (AI) is important, and how the topic will be tackled.
Armando Vieira, Bernardete Ribeiro

Chapter 5. Natural Language Processing and Speech

Deep learning (DL) has had a tremendous impact on natural language processing (NLP). After image and audio, probably this is the area where DL has unleashed the most transformative forces. For example, almost all projects related to NLP at Stanford University, one of the most respected institutions working on this area, involve DL research.
Armando Vieira, Bernardete Ribeiro

Chapter 6. Reinforcement Learning and Robotics

Because of the recent achievements of deep learning [GBC16] benefiting from big data, powerful computation, and new algorithmic techniques, you have been witnessing the renaissance of reinforcement learning, especially the combination of reinforcement learning and deep neural networks such as deep reinforcement learning (deep RL). Deep Q-networks (DQNs) have ignited the field of deep RL [MKS+15] by allowing machines to achieve superhuman performance in Atari games and the very hard board game of Go.
Armando Vieira, Bernardete Ribeiro

Deep Learning: Business Applications


Chapter 7. Recommendation Algorithms and E-commerce

E-commerce and digital marketing are becoming data-intensive areas. Deep learning can have a huge impact in these areas since high benefits can be achieved with marginal gains in accuracy. For instance, marginal improvements in the click-through rate (CTR) prediction or conversion ratio (CR) of users interacting with web content, either on PC or on mobile devices, may result in millions of dollars of savings in customer acquisition. However, this problem is becoming more complex as the user journey before product acquisition can be complex, with many contact points before purchase. Complex model attribution (the discovery of the trajectory of the user before buying a product) is thus necessary to correctly allocate the ad budget.
Armando Vieira, Bernardete Ribeiro

Chapter 8. Games and Art

One the most exciting areas of deep learning applications is the creative industries and games, either through algorithms to play traditional board games or video games or in the creation of virtual game characters or immersed reality. The recent success of AlphaGo, which beat the world Go champion, ignited the interest in AI bringing superhuman capabilities to machines.
Armando Vieira, Bernardete Ribeiro

Chapter 9. Other Applications

The range of deep learning applications goes well beyond the ones mentioned in previous chapters. This chapter will give an overview of other applications relevant for business. DL is already incorporated into many services and products, including customer service, finance, legal, sales, quality, pricing, and production.
Armando Vieira, Bernardete Ribeiro

Opportunities and Perspectives


Chapter 10. Business Impact of DL Technology

“I was a skeptic [about deep learning] for a long time, but the progress now is real. The results are real. It works.”
Armando Vieira, Bernardete Ribeiro

Chapter 11. New Research and Future Directions

Many supervised tasks in natural language processing, speech recognition, and automatic video analysis may soon become trivial through large RNNs. In the near future, both supervised learning RNNs and reinforcement learning will be greatly scaled up. Current large ANNs have on the order of a billion connections; soon that will be a trillion, at the same price. By comparison, human brains have a trillions of—much slower—connections.
Armando Vieira, Bernardete Ribeiro


Weitere Informationen

Premium Partner

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!