Closed JakobEliasWagner closed 6 months ago
The reason as to why this test fails is unrelated to eps. Removed the comment in 99d6b1a.
The previous plot is related to the range of the scaled tensor. The tests are performed for a range in the order of one -> 1e-7 is appropriate for testing.
I improved the docs a little and set the random seed, because tests failed from time to time.
Feature: Normalize
Description
This pull request introduces a new feature for data preprocessing: Z-Normalization. Z-Normalization, also known as standardization, is a technique used to scale data so that it has a mean of 0 and a standard deviation of 1. This process is essential in many machine learning algorithms as it ensures that each feature contributes equally to the analysis, improving the performance and stability of the models.
Which issue does this PR tackle?
How does it solve the problem?
Standardization
.How are the changes tested?
Checklist for Contributors
feature/title-slug
convention.Bugfix: Title
convention.Checklist for Reviewers: