Category Archives: Distributed learning

In my last post, I described the PageRank algorithm that was the basis for the original Google search. This week, I want to use PageRank to motivate the MapReduce framework for distributed data analysis. These days, MapReduce is beginning to fall … Continue reading →

At the end of June, I’m going to begin a new job as a software engineer in Google’s Cambridge office. For the past few months, preparing for this change has kept me too busy to write anything, but now that … Continue reading →

So far on this blog, my focus has been on conventional algorithms for data mining and machine learning, i.e. algorithms that can run on a standard desktop or laptop computer with a single processor. However, one of the trends in … Continue reading →