You're reading from Mastering Machine Learning Algorithms Expert techniques for implementing popular machine learning algorithms, fine-tuning your models, and understanding how they work

Product type Paperback

Published in Jan 2020

Publisher Packt

ISBN-13 9781838820299

Length 798 pages

Edition 2nd Edition

Languages

Python

Tools

Keras

Concepts

Machine Learning

Authors (2):

Giuseppe Bonaccorso

View More author details

Table of Contents (28) Chapters

Preface

1. Machine Learning Model Fundamentals

2. Loss Functions and Regularization FREE CHAPTER

3. Introduction to Semi-Supervised Learning

4. Advanced Semi-Supervised Classification

5. Graph-Based Semi-Supervised Learning

6. Clustering and Unsupervised Models

7. Advanced Clustering and Unsupervised Models

8. Clustering and Unsupervised Models for Marketing

9. Generalized Linear Models and Regression

10. Introduction to Time-Series Analysis

11. Bayesian Networks and Hidden Markov Models

12. The EM Algorithm

13. Component Analysis and Dimensionality Reduction

14. Hebbian Learning

15. Fundamentals of Ensemble Learning

16. Advanced Boosting Algorithms

17. Modeling Neural Networks

18. Optimizing Neural Networks

19. Deep Convolutional Networks

20. Recurrent Neural Networks

21. Autoencoders

22. Introduction to Generative Adversarial Networks

23. Deep Belief Networks

24. Introduction to Reinforcement Learning

25. Advanced Policy Estimation Algorithms

26. Other Books You May Enjoy

27. Index

The perceptron

The perceptron was the name that Frank Rosenblatt gave to the first neural model in 1957. A perceptron is a neural network with a single layer of input linear neurons, followed by an output unit based on the sign(x) function (alternatively, it's possible to consider a bipolar unit whose output is -1 and 1). The architecture of a perceptron is shown in the following diagram:

Structure of a perceptron

Even though the diagram might appear quite complex, a perceptron can be summarized by the following equation:

All the vectors are conventionally column-vectors; therefore, the dot product transforms the input into a scalar, then the bias is added, and the binary output is obtained using the step function, which outputs 1 when z > 0 and 0 otherwise. At this point, a reader could object that the step function is non-linear; however, a non-linearity applied to the output layer is only a filtering operation that has no effect on the actual...