Book Image

Machine Learning Fundamentals

By : Hyatt Saleh
Book Image

Machine Learning Fundamentals

By: Hyatt Saleh

Overview of this book

As machine learning algorithms become popular, new tools that optimize these algorithms are also developed. Machine Learning Fundamentals explains you how to use the syntax of scikit-learn. You'll study the difference between supervised and unsupervised models, as well as the importance of choosing the appropriate algorithm for each dataset. You'll apply unsupervised clustering algorithms over real-world datasets, to discover patterns and profiles, and explore the process to solve an unsupervised machine learning problem. The focus of the book then shifts to supervised learning algorithms. You'll learn to implement different supervised algorithms and develop neural network structures using the scikit-learn package. You'll also learn how to perform coherent result analysis to improve the performance of the algorithm by tuning hyperparameters. By the end of this book, you will have gain all the skills required to start programming machine learning algorithms.
Table of Contents (9 chapters)
Machine Learning Fundamentals
Preface

Performance Analysis


In the following section, we will first perform error analysis using the accuracy metric as a tool to determine the condition that is affecting the performance of the algorithm in greater proportion. Once the model is diagnosed, the hyperparameters can be tuned to improve the overall performance of the algorithm. The final model will be compared to those that were created during the previous chapter in order to determine whether a neural network outperforms the other models.

Error Analysis

Using the accuracy score calculated in Activity 14, we can calculate the error rates for each of the sets and compare them against each other to diagnose the condition that is affecting the model. To do so, a Bayes Error equal to 1% will be assumed, considering that other models in the previous chapter were able to achieve an accuracy level over 97%:

Figure 5.11: Accuracy score and error rate of the network

Note

Remember that in order to detect the condition that is affecting the network...