Search
Now showing items 1-10 of 13
Learning Generic Invariances in Object Recognition: Translation and Scale
(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 ...
Does invariant recognition predict tuning of neurons in sensory cortex?
(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 ...
Nonparametric Sparsity and Regularization
(2011-09-26)
In this work we are interested in the problems of supervised learning and variable selection when the input-output dependence is described by a nonlinear function depending on a few variables. Our goal is to consider a ...
Learning and Invariance in a Family of Hierarchical Kernels
(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 ...
Multi-Output Learning via Spectral Filtering
(2011-01-24)
In this paper we study a class of regularized kernel methods for vector-valued learning which are based on filtering the spectrum of the kernel matrix. The considered methods include Tikhonov regularization as a special ...
Neurons That Confuse Mirror-Symmetric Object Views
(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 ...
Regularization Predicts While Discovering Taxonomy
(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 ...
GURLS: a Toolbox for Regularized Least Squares Learning
(MIT CSAIL, 2012-01-31)
We present GURLS, a toolbox for supervised learning based on the regularized least squares algorithm. The toolbox takes advantage of all the favorable properties of least squares and is tailored to deal in particular with ...
Multiscale Geometric Methods for Data Sets I: Multiscale SVD, Noise and Curvature
(2012-09-08)
Large data sets are often modeled as being noisy samples from probability distributions in R^D, with D large. It has been noticed that oftentimes the support M of these probability distributions seems to be well-approximated ...
The computational magic of the ventral stream: sketch of a theory (and why some deep architectures work).
(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 ...