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

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

Chapter 8 – Solving the XOR Problem with a Feedforward Neural Network

Can the perceptron alone solve the XOR problem? (Yes | No)
Yes. The answer would have been no in 1969. A neural network, or some other mathematical process, is necessary to solve this problem. For the record, this is a common problem for electric circuits that function with "feedforward" electricity, and was solved long ago.
Is the XOR function linearly non-separable? (Yes | No)
The answer is no if you use a single neuron, and yes if you use a hidden layer with at least two neurons. That is a major problem to address in deep learning. If you cannot separate the features of a face, for example, in a picture, recognizing that face will prove difficult. Imagine a picture with one half of the face in shadow and the other half in bright sunlight. Since the eye and features of one half are in shadow, a poor deep learning program might only capture half...