Recurrent Online Clustering as a Spatio-Temporal Feature Extractor in DeSTIN
This is an incremental improvement for deep learning researchers working on scalable architectures.
The paper tackled the problem of capturing temporal features in the DeSTIN deep learning architecture by replacing explicit transition tables with a simpler feedback-based clustering mechanism, achieving state-of-the-art results on the MNIST classification benchmark.
This paper presents a basic enhancement to the DeSTIN deep learning architecture by replacing the explicitly calculated transition tables that are used to capture temporal features with a simpler, more scalable mechanism. This mechanism uses feedback of state information to cluster over a space comprised of both the spatial input and the current state. The resulting architecture achieves state-of-the-art results on the MNIST classification benchmark.