Book Image

Mobile Artificial Intelligence Projects

By : Karthikeyan NG, Arun Padmanabhan, Matt R. Cole
Book Image

Mobile Artificial Intelligence Projects

By: Karthikeyan NG, Arun Padmanabhan, Matt R. Cole

Overview of this book

We’re witnessing a revolution in Artificial Intelligence, thanks to breakthroughs in deep learning. Mobile Artificial Intelligence Projects empowers you to take part in this revolution by applying Artificial Intelligence (AI) techniques to design applications for natural language processing (NLP), robotics, and computer vision. This book teaches you to harness the power of AI in mobile applications along with learning the core functions of NLP, neural networks, deep learning, and mobile vision. It features a range of projects, covering tasks such as real-estate price prediction, recognizing hand-written digits, predicting car damage, and sentiment analysis. You will learn to utilize NLP and machine learning algorithms to make applications more predictive, proactive, and capable of making autonomous decisions with less human input. In the concluding chapters, you will work with popular libraries, such as TensorFlow Lite, CoreML, and PyTorch across Android and iOS platforms. By the end of this book, you will have developed exciting and more intuitive mobile applications that deliver a customized and more personalized experience to users.
Table of Contents (12 chapters)
PyTorch Experiments on NLP and RNN
TensorFlow on Mobile with Speech-to-Text with the WaveNet Model
Implementing GANs to Recognize Handwritten Digits

Artificial Intelligence Concepts and Fundamentals

This chapter acts as a prelude to the entire book and the concepts within it. We will understand these concepts at a level high enough for us to appreciate what we will be building throughout the book.

We will start by getting our head around the general structure of Artificial Intelligence (AI) and its building blocks by comparing AI, machine learning, and deep learning, as these terms can be used interchangeably. Then, we will skim through the history, evolution, and principles behind Artificial Neural Networks (ANNs). Later, we will dive into the fundamental concepts and terms of ANNs and deep learning that will be used throughout the book. After that, we take a brief look at the TensorFlow Playground to reinforce our understanding of ANNs. Finally, we will finish off the chapter with thoughts on where to get a deeper theoretical reference for the high-level concepts of the AI and ANN principles covered in this chapter, which will be as follows:

  • AI versus machine learning versus deep learning
  • Evolution of AI
  • The mechanics behind ANNs
  • Biological neurons
  • Working of artificial neurons
  • Activation and cost functions
  • Gradient descent, backpropagation, and softmax
  • TensorFlow Playground