Scalable Deep Learning for Image Classification with K-Means and Logistic Regression

With lot of research and advancement of deep learning, complex unsupervised learning is applied for extracting deep hierarchies of features especially to images. But, off-the-shelf unsupervised learning algorithms combined with deep learning techniques would yield results similar to complext,time consuming Deep learning algorithms. In this report, I would use K-means algorithm based on [1][3] and apply logistic regression to NORB and CIFAR datasets using single-layer network to classify images.