Book Image

Hands-On Artificial Intelligence for Beginners

By : Patrick D. Smith, David Dindi
Book Image

Hands-On Artificial Intelligence for Beginners

By: Patrick D. Smith, David Dindi

Overview of this book

Virtual Assistants, such as Alexa and Siri, process our requests, Google's cars have started to read addresses, and Amazon's prices and Netflix's recommended videos are decided by AI. Artificial Intelligence is one of the most exciting technologies and is becoming increasingly significant in the modern world. Hands-On Artificial Intelligence for Beginners will teach you what Artificial Intelligence is and how to design and build intelligent applications. This book will teach you to harness packages such as TensorFlow in order to create powerful AI systems. You will begin with reviewing the recent changes in AI and learning how artificial neural networks (ANNs) have enabled more intelligent AI. You'll explore feedforward, recurrent, convolutional, and generative neural networks (FFNNs, RNNs, CNNs, and GNNs), as well as reinforcement learning methods. In the concluding chapters, you'll learn how to implement these methods for a variety of tasks, such as generating text for chatbots, and playing board and video games. By the end of this book, you will be able to understand exactly what you need to consider when optimizing ANNs and how to deploy and maintain AI applications.
Table of Contents (15 chapters)

CNNs for image tagging

Let's work on putting our new knowledge of CNNs to the test. We're going to work through one of the most popular tasks for CNNs: image classification.

In an image classification task, our horse looks at a given image and determines the probability that a certain object is an image. In the following example, the image is 248 pixels wide, 400 pixels tall, and has three color channels: red, green, and blue (RGB). Therefore, the image consists of 248 x 400 x 3 numbers, or a total of 2,97, 600 numbers. Our job is to turn these numbers into a single classified label; is this horse?

While this might seem a simple task for a human to perform, there are many challenges in trying to complete this with a computer:

  • Clouded vision: An image of an object could be blurry
  • Variation in point of view: An object could be seen from a variety of 360-degree views...