Articles

Dimensionality reduction through autoencoders

[Article] [Github]

Neural networks that can learn to compress input data into a lower-dimensional representation while preserving the most important patterns and relationships.

Class Imbalance  

[Article][Github]

Class Imbalance is a common challenge in statistics and machine learning where the distribution of the target variable is skewed,  resulting in several issues such as bias towards the majority class or over-fitting.

However, and since machine learning is application and experimentation driven, class imbalance should not be handled in a nomothetic manner.