- Working Paper
Despite its size and complexity, the human cortex exhibits striking anatomical regularities, suggesting there may simple meta-algorithms underlying cortical learning and computation. We expect such meta-algorithms to be of interest since they need to operate quickly, scalably and effectively with little-to-no specialized assumptions. This note focuses on a speciﬁc question: How can neurons use vast quantities of unlabeled data to speed up learning from the comparatively rare labels provided by reward systems? As a partial answer, we propose randomized co-training as a biologically plausible meta-algorithm satisfying the above requirements. As evidence, we describe a biologically-inspired algorithm, Correlated Nyström Views (XNV) that achieves state-of-the-art performance in semi-supervised learning, and sketch work in progress on a neuronal implementation Show more
External linksSearch via SFX
Book titleRandomized Methods for Machine Learning (NIPS workshop)
PublisherNeural Information Processing Systems (NIPS) Foundation
Organisational unit03659 - Buhmann, Joachim M.
MoreShow all metadata