Clustering report
Download as PPTX, PDF0 likes57 views
This document discusses clustering clean and adversarial images from the MNIST dataset using K-means, LDA, and T-SNE clustering methods. It contains 10,000 clean images and 10,000 adversarial images generated using the FGSM attack method from 10 classes in MNIST. The document applies principal component analysis to extract features from the images before clustering them to visualize how the different methods group the clean and adversarial samples.
1 of 6
Download to read offline
More Related Content
More from Kishor Datta Gupta (20)
Ad
Recently uploaded (20)
Ad
Clustering report
- 1. Clustering Adversarial vs Non Adversarial Kishor Datta Gupta
- 2. Data Dataset MNIST 10000 Clean images from 10 class 10000 FGSM attack method from 10 class Data extraction method: PCA Clustering Method: • K-Means • LDA • T-SNE