Principal Component Classification

TL;DR

This paper introduces a PCA-based classification method that learns features with class scores, resulting in an efficient encoder-decoder model suitable for supervised learning and effective across multiple datasets.

Contribution

It presents a novel PCA-based approach for direct classification that combines feature learning with class score encoding in a computationally efficient model.

Findings

Performs well on several datasets

Has an encoder-decoder structure for supervised learning

Offers computational efficiency

Abstract

We propose to directly compute classification estimates by learning features encoded with their class scores using PCA. Our resulting model has a encoder-decoder structure suitable for supervised learning, it is computationally efficient and performs well for classification on several datasets.