On a model of visual cortex: learning invariance and selectivity

نویسندگان

  • Andrea Caponnetto
  • Tomaso Poggio
  • Steve Smale
چکیده

In this paper we present a class of algorithms for similarity learningon spaces of images. The general framework that we introduce is mo-tivated by some well-known hierarchical pre-processing architectures forobject recognition which have been developed during the last decade, andwhich have been in some cases inspired by functional models of the ven-tral stream of the visual cortex. These architectures are characterized by theconstruction of a hierarchy of “local” feature representations of the visualstimulus. We show that our framework includes some well-known tech-niques, and that it is suitable for the analysis of dynamic visual stimuli,presenting a quantitative error analysis in this setting.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

On a model of visual cortex: learning invariance and selectivity from image sequences

In this paper we present a class of algorithms for similarity learningon spaces of images. The general framework that we introduce is mo-tivated by some well-known hierarchical pre-processing architectures forobject recognition which have been developed during the last decade, andwhich have been in some cases inspired by functional models of the ven-tral stream of the vi...

متن کامل

Investigating Nonlinearities in the Standard Model of Object Recognition

The Problem: The standard model of object recognition in cortex is a computational model of ventral pathway thought tomediate visual object recognition [5]. It is composed of hierarchical feedforward layers of neuron-like units, performing either (1) template matching with a Gaussian function to increase feature complexity or (2) nonlinear pooling with a maximum operation to increase translatio...

متن کامل

On Invariance in Hierarchical Models

A goal of central importance in the study of hierarchical models for object recognition – and indeed the mammalian visual cortex – is that of understanding quantitatively the trade-off between invariance and selectivity, and how invariance and discrimination properties contribute towards providing an improved representation useful for learning from data. In this work we provide a general group-...

متن کامل

Iterative Orientation Tuning of Simple Cells in V1: A Comparative Study of Two Computational Models for Contrast Detection in Images

The orientation selectivity of simple cells in visual cortex gives a striking example of the biological system perfectly adapted to the perception pf oriented stimuli. Several models have employed major principles of orientation selectivity for the processing of contrast variations in images. We have recently suggested a model for iterative orientation tuning, in which the astonishingly regular...

متن کامل

Can ovariectomy and learning affect prefrontal cortex GABAAα1 receptor distribution in passive avoidance model in rats?

Introduction: The interaction between steroid hormones and neurotransmitters such as GABA has been proved. The regulation of muscimol binding to high-affinity GABAA receptors by estradiol and progesterone has been studied within distinct brain regions using in vitro quantitative autoradiography. There are few studies about the mechanism of the effect of steroid hormones on behaviors such as ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008