Intuition Behind Whitening Image Patches
In the Stanford Deep Learning tutorial, whitening is introduced as a powerful pre-processing step for feature learning.
In the Stanford Deep Learning tutorial, whitening is introduced as a powerful pre-processing step for feature learning.
Many machine learning techniques make use of distance calculations as a measure of similarity between two points. For example, in k-means clustering, we assign data points to clusters by calculating and comparing the distances to each of the cluster centers. Similarly, Radial Basis Function (RBF) Networks, such as the RBF SVM, also make use of the distance between the input vector and stored prototypes to perform classification.
This post covers the sections of the tutorial titled “Self-Taught Learning and Unsupervised Feature Learning” and “Building Deep Networks for Classification”.
Softmax regression is a generalized form of logistic regression which can be used in multi-class classification problems where the classes are mutually exclusive. The hand-written digit dataset used in this tutorial is a perfect example. A softmax regression classifier trained on the hand written digits will output a separate probability for each of the ten digits, and the probabilities will all add up to 1.