Clustering Learning for Robotic Vision

Eugenio Culurciello, Jordan Bates, Aysegul Dundar, Jose Carrasco, Clement Farabet

Jan 15, 2013 (modified: Jan 15, 2013) ICLR 2013 conference submission readers: everyone
  • Decision: conferencePoster-iclr2013-workshop
  • Abstract: We present the clustering learning technique applied to multi-layer feedforward deep neural networks. We show that this unsupervised learning technique can compute network filters with only a few minutes and a much reduced set of pa- rameters. The goal of this paper is to promote the technique for general-purpose robotic vision systems. We report its use in static image datasets and object track- ing datasets. We show that networks trained with clustering learning can outper- form large networks trained for many hours on complex datasets.