Data Representation and Compression Using Linear-Programming Approximations
international conference on learning representations, Volume abs/1511.06606, 2016.
Abstract: We propose `Draculau0027, a new framework for unsupervised feature selection from sequential data such as text. Dracula learns a dictionary of $n$-grams that efficiently compresses a given corpus and recursively compresses its own dictionary; in effect, Dracula is a `deepu0027 extension of Compressive Feature Learning. It requir...More
PPT (Upload PPT)