PCA - Principal Component Analysis

PCA is a dimensional reductionality technique used to handle data with high sparsity (data cursed with high dimensionality). The idea is to extract a limited number of significant features for training the model based on the extent of correlation between the features. The current repository involves in extracting 24 most significant vector components from a high dimensional data, visualizing them and reconstructing the images back again using only the signficant vector features to see the extent of information loss.