MIT Libraries homeMIT Libraries logoDSpace@MIT

MIT
Search 
  • DSpace@MIT Home
  • Computer Science and Artificial Intelligence Lab (CSAIL)
  • Search
  • DSpace@MIT Home
  • Computer Science and Artificial Intelligence Lab (CSAIL)
  • Search
JavaScript is disabled for your browser. Some features of this site may not work without it.

Search

Show Advanced FiltersHide Advanced Filters

Filters

Use filters to refine the search results.

Now showing items 1-10 of 10

  • Sort Options:
  • Relevance
  • Title Asc
  • Title Desc
  • Issue Date Asc
  • Issue Date Desc
  • Results Per Page:
  • 5
  • 10
  • 20
  • 40
  • 60
  • 80
  • 100
Thumbnail

Generalization and Properties of the Neural Response 

Bouvrie, Jake; Poggio, Tomaso; Rosasco, Lorenzo; Smale, Steve; Wibisono, Andre (2010-11-19)
Hierarchical learning algorithms have enjoyed tremendous growth in recent years, with many new algorithms being proposed and applied to a wide range of applications. However, despite the apparent success of hierarchical ...
Thumbnail

The computational magic of the ventral stream: sketch of a theory (and why some deep architectures work). 

Poggio, Tomaso; Mutch, Jim; Leibo, Joel; Rosasco, Lorenzo; Tacchetti, Andrea (2012-12-29)
This paper explores the theoretical consequences of a simple assumption: the computational goal of the feedforward path in the ventral stream -- from V1, V2, V4 and to IT -- is to discount image transformations, after ...
Thumbnail

Learning and Invariance in a Family of Hierarchical Kernels 

Wibisono, Andre; Bouvrie, Jake; Rosasco, Lorenzo; Poggio, Tomaso (2010-07-30)
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 ...
Thumbnail

Learning Generic Invariances in Object Recognition: Translation and Scale 

Leibo, Joel Z; Mutch, Jim; Rosasco, Lorenzo; Ullman, Shimon; Poggio, Tomaso (2010-12-30)
Invariance to various transformations is key to object recognition but existing definitions of invariance are somewhat confusing while discussions of invariance are often confused. In this report, we provide an operational ...
Thumbnail

Neurons That Confuse Mirror-Symmetric Object Views 

Mutch, Jim; Leibo, Joel Z; Smale, Steve; Rosasco, Lorenzo; Poggio, Tomaso (2010-12-31)
Neurons in inferotemporal cortex that respond similarly to many pairs of mirror-symmetric images -- for example, 45 degree and -45 degree views of the same face -- have often been reported. The phenomenon seemed to be an ...
Thumbnail

Sufficient Conditions for Uniform Stability of Regularization Algorithms 

Poggio, Tomaso; Rosasco, Lorenzo; Wibisono, Andre (2009-12-01)
In this paper, we study the stability and generalization properties of penalized empirical-risk minimization algorithms. We propose a set of properties of the penalty term that is sufficient to ensure uniform ?-stability: ...
Thumbnail

Mathematics of the Neural Response 

Caponnetto, Andrea; Poggio, Tomaso; Bouvrie, Jake; Rosasco, Lorenzo; Smale, Steve (2008-11-26)
We propose a natural image representation, the neural response, motivated by the neuroscience of the visual cortex. The inner product defined by the neural response leads to a similarity measure between functions which we ...
Thumbnail

Multi-Class Learning: Simplex Coding And Relaxation Error 

Mroueh, Youssef; Poggio, Tomaso; Rosasco, Lorenzo; Slotine, Jean-Jacques E. (2011-09-27)
We study multi-category classification in the framework of computational learning theory. We show how a relaxation approach, which is commonly used in binary classification, can be generalized to the multi-class setting. ...
Thumbnail

Does invariant recognition predict tuning of neurons in sensory cortex? 

Poggio, Tomaso; Mutch, Jim; Anselmi, Fabio; Tacchetti, Andrea; Rosasco, Lorenzo; e.a. (2013-08-06)
Tuning properties of simple cells in cortical V1 can be described in terms of a "universal shape" characterized by parameter values which hold across different species. This puzzling set of findings begs for a general ...
Thumbnail

Regularization Predicts While Discovering Taxonomy 

Mroueh, Youssef; Poggio, Tomaso; Rosasco, Lorenzo (2011-06-03)
In this work we discuss a regularization framework to solve multi-category when the classes are described by an underlying class taxonomy. In particular we discuss how to learn the class taxonomy while learning a multi-category ...

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CommunityBy Issue DateAuthorsTitlesSubjects

My Account

Login

Discover

Author
Poggio, Tomaso (10)
Rosasco, Lorenzo (10)
Mutch, Jim (4)Bouvrie, Jake (3)Smale, Steve (3)Wibisono, Andre (3)Leibo, Joel Z (2)Mroueh, Youssef (2)Tacchetti, Andrea (2)Anselmi, Fabio (1)... View MoreSubjectartificial intelligence (2)computational learning (2)classification (1)computation (1)computer vision (1)convex relaxation (1)generic transformations (1)hierarchical learning (1)invariances of sensory perception (1)kernel methods (1)... View MoreDate Issued2010 (4)2011 (2)2008 (1)2009 (1)2012 (1)2013 (1)Has File(s)Yes (10)

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries homeMIT Libraries logo

Find us on

Twitter Instagram YouTube

MIT Libraries navigation

SearchHours & locationsBorrow & requestResearch supportAbout us
PrivacyPermissionsAccessibility
MIT
Massachusetts Institute of Technology
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.