Training of a neural network on large datasets could be a rather long and challenging thing. There are lots of approaches for reducing training time: parallelization, early stopping, momentum, dimensionality reduction etc. They provide faster convergence of training, prevent unnecessary iterations, utilize hardware resources in a more efficient way. In this post we'll see how good initialization can affect training. Continue reading PCA-based pretraining of neural networks
In the previous post we've reviewed logistic regression model and designed a simple clustering algorithm based on it. We have managed to get a decent clustering on a subset of MNIST dataset. Yet there were some drawbacks in our approach.
Continue reading Clustering via mutual information maximization. Part 2
In this series of posts we will learn logistic regression classifier in three ways: supervised, unsupervised and something in between. We will find out that for some machine learning problems you need only a few labels for your data to get a decent model. Continue reading Clustering via mutual information maximization. Part 1