From OpenCog

Jump to: navigation, search

Deep SpatioTemporal Inference Network (DeSTIN) is a scalable deep learning architecture that relies on a combination of unsupervised learning and Bayesian inference. The paper DeSTIN: A Scalable Deep Learning Architecture with Application to High-Dimensional Robust Pattern Recognition by Itamar Arel, Derek Rose, and Robert Coop describes this method.

Briefly put, DeSTIN uses online clustering algorithms to hierarchically create cetroids in a way that loosely mimics the way humans understand things. It can be loosely classified as a Deep Learning Network (DLN).

The OpenCog Foundation has adopted this academic project to prepare it for open-source release. Developers interested in working with us to these ends are invited to contact us.

DeSTIN source code and links to more papers are on GitHub at

Various notes & papers related to ways of implementing OpenCog with DeSTIN (DestinOpenCog)