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

Generating profit with transfer learning

Transfer learning means that we can use a model we designed and trained in another similar case. This will make the model very profitable since we do not have to design a new model and write a new program for every new case. You will thus generate profit for your company or customer by lowering the cost of new implementations of your trained model. Think of a good AI model as a reusable tool when applied to similar cases. This is why concept learning, being more general and abstract, is profitable. That is how we humans adapt.

When it comes to reasoning and thinking in general, we use mental images with some words. Our thoughts contain concepts, on which we build solutions.

The trained model from Chapter 9, Abstract Image Classification with Convolutional Neural Networks (CNNs), can now classify images of a certain type. In this section, the trained model will be loaded and then generalized through transfer learning...