MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • Computer Science and Artificial Intelligence Lab (CSAIL)
  • CSAIL Digital Archive
  • CSAIL Technical Reports (July 1, 2003 - present)
  • View Item
  • DSpace@MIT Home
  • Computer Science and Artificial Intelligence Lab (CSAIL)
  • CSAIL Digital Archive
  • CSAIL Technical Reports (July 1, 2003 - present)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Learning and Invariance in a Family of Hierarchical Kernels

Author(s)
Wibisono, Andre; Bouvrie, Jake; Rosasco, Lorenzo; Poggio, Tomaso
Thumbnail
DownloadMIT-CSAIL-TR-2010-035.pdf (672.5Kb)
Other Contributors
Center for Biological and Computational Learning (CBCL)
Advisor
Tomaso Poggio
Metadata
Show full item record
Abstract
Understanding invariance and discrimination properties of hierarchical models is arguably the key to understanding how and why such models, of which the the mammalian visual system is one instance, can lead to good generalization properties and reduce the sample complexity of a given learning task. In this paper we explore invariance to transformation and the role of layer-wise embeddings within an abstract framework of hierarchical kernels motivated by the visual cortex. Here a novel form of invariance is induced by propagating the effect of locally defined, invariant kernels throughout a hierarchy. We study this notion of invariance empirically. We then present an extension of the abstract hierarchical modeling framework to incorporate layer-wise embeddings, which we demonstrate can lead to improved generalization and scalable algorithms. Finally we analyze experimentally sample complexity properties as a function of architectural parameters.
Date issued
2010-07-30
URI
http://hdl.handle.net/1721.1/57464
Series/Report no.
CBCL-290MIT-CSAIL-TR-2010-035
Keywords
artificial intelligence

Collections
  • CSAIL Technical Reports (July 1, 2003 - present)

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.