Unsupervised Learning of Individuals and Categories from Images

Stephen Waydo, Christof Koch
2008 Neural Computation  
Motivated by the existence of highly selective, sparsely firing cells observed in the human medial temporal lobe (MTL), we present an unsupervised method for learning and recognizing object categories from unlabeled images. In our model, a network of nonlinear neurons learns a sparse representation of its inputs through an unsupervised expectationmaximization process. We show that the application of this strategy to an invariant feature-based description of natural images leads to the
more » ... t of units displaying sparse, invariant selectivity for particular individuals or image categories much like those observed in the MTL data.
doi:10.1162/neco.2007.03-07-493 pmid:18194101 fatcat:4m5woeqzrfhfhenfxym4i2dgmy