Whether you want to compress an image or calculate pseudo-inverse, SVD will always be there for you.
SVM is the Mr. Perfect of Machine Learning Classifiers. It basically wants different examples to be as far as possible.
A few problems for the ones looking to test their learning.
Notes on the regularization method Dropout.
This blog contains a guide to get started with Deep Learning as well as get in-depth knowledge of the field.
Notes on the the InceptionNet CNN architecture.
Notes on Linear Algebra from the DL Book.
Notes on the Net2Net architecture.
Notes on Probability and Information Theory from the DL Book.
Notes on the object detection architecture RCNN.