Book Image

Artificial Intelligence By Example

By : Denis Rothman
Book Image

Artificial Intelligence By Example

By: Denis Rothman

Overview of this book

Artificial intelligence has the potential to replicate humans in every field. Artificial Intelligence By Example serves as a starting point for you to understand how AI is built, with the help of intriguing examples and case studies. Artificial Intelligence By Example will make you an adaptive thinker and help you apply concepts to real-life scenarios. Using some of the most interesting AI examples, right from a simple chess engine to a cognitive chatbot, you will learn how to tackle the machine you are competing with. You will study some of the most advanced machine learning models, understand how to apply AI to blockchain and IoT, and develop emotional quotient in chatbots using neural networks. You will move on to designing AI solutions in a simple manner rather than get confused by complex architectures and techniques. This comprehensive guide will be a starter kit for you to develop AI applications on your own. By the end of this book, you will have understood the fundamentals of AI and worked through a number of case studies that will help you develop your business vision.
Table of Contents (19 chapters)

Building a feedforward neural network from scratch

Let's get into a time machine. In nanoseconds, it takes us back to 1969. We have today's knowledge but nothing to prove it. Minsky and Papert have just published their book, Perceptrons. They've proven that a perceptron cannot implement the exclusive OR function XOR.

We are puzzled. We know that deep learning will be a great success in the 21st century. We want to try to change the course of history. Thanks to our time machine, we land in a small apartment. It's comfortable, with a vinyl record playing the music we like! There is a mahogany desk with a pad, a pencil, sharpener, and eraser waiting for us. We sit. A warm cup of coffee appears in a big mug. We're ready to solve the XOR problem from scratch. We have to find a way to classify those dots with a neural network.

...