You're reading from Artificial Intelligence By Example Acquire advanced AI, machine learning, and deep learning design skills

Product type Paperback

Published in Feb 2020

Publisher Packt

ISBN-13 9781839211539

Length 578 pages

Edition 2nd Edition

Languages

Python

Tools

TensorFlow

Concepts

Artificial Intelligence

Author (1):

Denis Rothman

View More author details

Table of Contents (23) Chapters

Preface

1. Getting Started with Next-Generation Artificial Intelligence through Reinforcement Learning

2. Building a Reward Matrix – Designing Your Datasets FREE CHAPTER

3. Machine Intelligence – Evaluation Functions and Numerical Convergence

4. Optimizing Your Solutions with K-Means Clustering

5. How to Use Decision Trees to Enhance K-Means Clustering

6. Innovating AI with Google Translate

7. Optimizing Blockchains with Naive Bayes

8. Solving the XOR Problem with a Feedforward Neural Network

9. Abstract Image Classification with Convolutional Neural Networks (CNNs)

10. Conceptual Representation Learning

11. Combining Reinforcement Learning and Deep Learning

12. AI and the Internet of Things (IoT)

13. Visualizing Networks with TensorFlow 2.x and TensorBoard

14. Preparing the Input of Chatbots with Restricted Boltzmann Machines (RBMs) and Principal Component Analysis (PCA)

15. Setting Up a Cognitive NLP UI/CUI Chatbot

16. Improving the Emotional Intelligence Deficiencies of Chatbots

17. Genetic Algorithms in Hybrid Neural Networks

18. Neuromorphic Computing

19. Quantum Computing

20. Answers to the Questions

21. Other Books You May Enjoy

22. Index

Abstract Image Classification with Convolutional Neural Networks (CNNs)

The invention of convolutional neural networks (CNNs) applied to vision represents by far one of the most innovative achievements in the history of applied mathematics. With their multiple layers (visible and hidden), CNNs have brought artificial intelligence from machine learning to deep learning.

In Chapter 8, Solving the XOR Problem with a Feedforward Neural Network, we saw that f(x, w) is the building block of any neural network. A function f will transform an input x with weights w to produce an output. This output can be used as such or fed into another layer. In this chapter, we will generalize this principle and introduce several layers. At the same time, we will use datasets with images. We will have a dataset for training and a dataset for validation to confirm that our model works.

A CNN relies on two basic tools of linear algebra: kernels and functions, applying...