2013/10/24 by David Balduzzi, Balduzzi, David
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Mathematics · #Advanced Memory and Neural Computing #FOS: Biological sciences #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Reservoir Computing #Neurons and Cognition (q-bio.NC) #cs.LG #q-bio.NC #stat.ML
paper · pdf · doi:10.48550/arxiv.1310.6536
NIPS workshop: Randomized methods for machine learning
arxiv created 2013/10/24 · openalex publication_date 2013/10/24 · arxiv updated 2013/10/25 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28
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 Nystrom Views (XNV) that achieves state-of-the-art performance in semi-supervised learning, and sketch work in progress on a neuronal implementation.