Articles in the Data Science category

  1. Dimensional Reduction Through The Principle Of Reconstruction

    Dimensional Reduction

    Dimensional reduction is the process of assigning high-dimensional stimuli to locations in a lower-dimensional space in such a way that the relations between the high-dimensional stimuli are recreated or preserved by their low-dimensional analogs. It is a process that has many applications, including information compression, noise attenuation, the …

  2. Efficient Querying Of Google Books Ngram Data

    The Google Books Ngram Data (raw data available here) is a pretty amazing resource. Version 2, released in July 2012, contains 1gram through 5gram frequency counts derived from 6% of all books ever published (!).

    There's clearly a lot an enterprising young gentleman or gentlewoman could accomplish with a resource such …