next up previous
Next: A. THE PREDICTOR NETWORK Up: SEQUENTIAL NEURAL TEXT COMPRESSION Previous: II. BASIC APPROACH

III. OFF-LINE METHODS

In what follows, we will first describe the training phase of the predictor network $P$ (a strictly layered feed-forward net trained by back-propagation [10][4]). The training phase is based on a set $F$ of training files. Then we will describe three working off-line variants of ``compress'' and ``uncompress'' functions based on $P$. All methods are guaranteed to encode and decode arbitrary unknown text files without loss of information.



Subsections

Juergen Schmidhuber 2003-02-13