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

Exploring the output of the layers of a CNN in two steps with TensorFlow

Many corporate contracts in the field of business intelligence require an explanation process for any algorithm that makes automatic and critical decisions. It is often mandatory for the editor of algorithms, artificial intelligence or not, to provide an explanation. We need to be prepared for that.

Also, maintenance becomes critical once artificial intelligence runs in production. Developers often move from one department to another, from one company to another. The person that has to maintain the program needs to understand it in detail.

Exploring and visualizing a CNN is a good way to get our hands dirty, open the hood of our roadster and see how the engine works!

First, we will first build the CNN layer by layer. We will be building the sequential classifier with TensorFlow 2 from the bottom to the top.
We will not be using a Keras model directly; we'll use TensorFlow...