How Can We Be So Dense? The Robustness of Highly Sparse Representations

Click on the image above to enlarge

Abstract:

This poster, which is based on a paper by the same name, proposes that sparsity should be a key design principle for robustness. Numenta VP Research Subutai Ahmad presented this poster and a presentation on the topic at an ICML 2019 workshop on Uncertainty & Robustness in Deep Learning.

For additional resources on this topic from ICML, you can view a recording of Subutai’s talk and download the slides from his presentation.