Book Image

Hands-On Convolutional Neural Networks with TensorFlow

By : Iffat Zafar, Giounona Tzanidou, Richard Burton, Nimesh Patel, Leonardo Araujo
Book Image

Hands-On Convolutional Neural Networks with TensorFlow

By: Iffat Zafar, Giounona Tzanidou, Richard Burton, Nimesh Patel, Leonardo Araujo

Overview of this book

Convolutional Neural Networks (CNN) are one of the most popular architectures used in computer vision apps. This book is an introduction to CNNs through solving real-world problems in deep learning while teaching you their implementation in popular Python library - TensorFlow. By the end of the book, you will be training CNNs in no time! We start with an overview of popular machine learning and deep learning models, and then get you set up with a TensorFlow development environment. This environment is the basis for implementing and training deep learning models in later chapters. Then, you will use Convolutional Neural Networks to work on problems such as image classification, object detection, and semantic segmentation. After that, you will use transfer learning to see how these models can solve other deep learning problems. You will also get a taste of implementing generative models such as autoencoders and generative adversarial networks. Later on, you will see useful tips on machine learning best practices and troubleshooting. Finally, you will learn how to apply your models on large datasets of millions of images.
Table of Contents (17 chapters)
Title Page
Copyright and Credits
Packt Upsell

Chapter 2. Deep Learning and Convolutional Neural Networks

efore we begin this chapter, we need to talk a bit about AI and machine learning (ML) and how those two components fit together. The term "artificial" refers to something that is not real or natural, whereas "intelligence" refers to something capable of understanding, learning, or able to solve problems (and, in extreme cases, being self-aware).

Officially, artificial intelligence research began at the Dartmouth Conference of 1956 where AI and its mission were defined. In the following years, everyone was optimistic as machines were able to solve algebra problems and learn English, and the first robot was constructed in 1972. However in the 1970s, due to overpromising but under delivering, there was a so-called AI winter where AI research was limited and underfunded. After this though AI was reborn through expert systems, that could display human-level analytical skills. Afterwards, a second AI winter machine learning got recognized...