Recurrent Sliding Windows for WEKA

Recurrent Sliding Windows provide a way of converting a sequential supervised learning problem into a traditional supervised learning problem. In sequential supervised learning, the task is to assign a class label to each element of a sequence. Each training example consists of a sequence of feature vectors and a corresponding sequence of labels.

Saket Joshi wrote a package that extends the WEKA system to use Recurrent Sliding Windows. Download and untar the tar file listed here and read the README.txt file for further information.

Download Java Recurrent Sliding Window Package for WEKA.

Updated as of Mon Apr 25 11:21:56 2005. Works with WEKA 3.4.4. There is a known bug that prevents it from working with later versions. We currently do not have any plans to fix this (sorry).