Saturday, 12 September 2015

Mining Massive Datasets by Stanford University on Coursera.

Mining Massive Datasets by Stanford University on Coursera.

Let the fun begin ... 

 In the next seven weeks, we will present to you many of the important tools for extracting information from very large datasets.  Each week there will be a number of videos to watch, and one or more homeworks to do.  The materials are backed up by a free on-line textbook, also published by Cambridge University Press, also called "Mining of Massive Datasets."  You can download the book at

The first week is devoted to two topics:

  1. MapReduce: A programming system for easily implementing parallel algorithms on commodity clusters.  This material is in the first four videos available for the week.
  2. Link Analysis: The remaining seven videos discuss the PageRank algorithm that made Google more effective than previous search engines.
There is also a single homework covering both topics.  This homework is classified as "Basic."  See below for an explanation of basic vs. advanced work, and the significance.

No comments:

Post a Comment

Datanami, Woe be me