musings about machine learning
tl;dr: We can use compression algorithms (like the well-known zip file compression) for machine learning purposes, specifically for classifying hand-written digits (MNIST). Code available: https://github.com/BlackHC/mnist_by_zip.
In Active Learning we use a “human in the loop” approach to data labelling, reducing the amount of data that needs to be labelled drastically, and making machine learning applicable when labelling costs would be too high otherwise. In our paper  we present BatchBALD: a new practical method for choosing batches of informative points in Deep Active Learning which avoids labelling redundancies that plague existing methods. Our approach is based on information theory and expands on useful intuitions. We have also made our implementation available on GitHub at https://github.com/BlackHC/BatchBALD.