An example of a minimum distance classificator doing a comparison between using Mahalanobis distance and Euclidean distance.

Project on extending a Neural Partitioner for the M149 - Database Systems course, NKUA, Spring 2023.

B.Tech Final Project Paper

Customer Segmentation using mahalonobis and minkowsi distance

Our solution for Fujitsu LOD4ALL 2016 hackathon

These projects were carried out as part of the MATH2021-1 High-dimensional data analysis course of the ULiege.

Classification using KNN on Vertebral Column Data Set

As Tensorflow Kennard-Stone algorithmin uses euclidean distances, the need for an adaptation arrises when dealing with a big vector space that has unknown correlations between its variables, it may improve a lot neural networks performance.

Classification of IRIS Dataset using various distance metrics.

The transformer that transforms data so to squared norm of transformed data becomes Mahalanobis' distance.

The code for large margin metric learning for nearest neighbor classification and its acceleration using triplet mining and stratified sampling

PySpark unofficial implementation of the study "Home monitoring for older singles: A gas sensor array system"

Robust object tracking using neural network based instance segmentation via probabilistic graphical models (PGMs)

As Tensorflow Kennard-Stone algorithmin uses euclidean distances, the need for an adaptation arrises when dealing with a big vector space that has unknown correlations between its variables, it may improve a lot neural networks performance.

使用纯python实现KNN和马氏距离算法，不含sklearn等高级包

Application of Multivariate Statistics on customer’ habits features to obtain a Customer segmentation of a wholesale shop.

Leveraging latent representations for efficient textual OOD detection

Finding Covariance Matrix, Correlation Coefficient, Euclidean and Mahalanobis Distance

Outlier detection tool for graph datasets

This repository is about the implementation of Mahalanobis Distance outlier detection as a one class classification model. This has been achieved using Python