Browsed by
Tag: Machine learning

K-Means clustering of MNIST dataset

K-Means clustering of MNIST dataset

Updates as on 16th Jan 2020: Improved clustering accuracy to 98.5% using a simpler CNN model mentioned in Keras page. And instead of extracting a feature vector from the final activation layer, we should take the output of the layer just before the final activation layer. In this post, we will be clustering MNIST digits dataset using the K-Means algorithm with accuracy close to 90%. And also we will understand different aspects of extracting features from images, and see how…

Read More Read More