A number of people have asked me, in response to my tutorial on Radial Basis Function Networks (RBFNs) for classification, about how you would apply an RBFN to function approximation or regression (and for Matlab code to do this, which you can find at the end of the post).
I’ve spent some time playing with the document clustering example in scikit-learn and I thought I’d share some of my results and insights here for anyone interested.
In this post, I’m providing a brief tutorial, along with some example Python code, for applying the MinHash algorithm to compare a large number of documents to one another efficiently.
I thought I’d share briefly some of our team’s recent experiences in renting time on GPUs for machine learning work.
In this post, I provide a detailed description and explanation of the Convolutional Neural Network example provided in Rasmus Berg Palm’s DeepLearnToolbox for MATLAB. His example code applies a relatively simple CNN with 2 hidden layers and only 18 neurons to the MNIST dataset. The CNN’s accuracy is 98.92% on the test set, which seems very impressive to me given the small number of neurons.