Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. Computer Science and Artificial Intelligence Lab (CSAIL)
  3. Artificial Intelligence Lab Publications
  4. AI Memos (1959 - 2004)
  5. Observations on Cortical Mechanisms for Object Recognition andsLearning

Observations on Cortical Mechanisms for Object Recognition andsLearning

Thumbnail Image
Download
Name

AIM-1404.pdf

Size

1.01 MB

Format

Adobe PDF

Checksum (MD5)

6079dfee6c983a18c4cab095dda0ae94

Thumbnail Image
Download
Name

AIM-1404.ps.Z

Size

266.24 KB

Format

Unknown

Checksum (MD5)

41a35baa35de154174f893f0f0bea539

Author(s)
Poggio, Tomaso
•
Hurlbert, Anya
Date Issued
December 1, 1993
Series/Report no.
AIM-1404
CBCL-077
Abstract
This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on a recent computational model. The view-centered scheme relies on modules for learning from examples, such as Hyperbf-like networks. Such models capture a class of explanations we call Memory-Based Models (MBM) that contains sparse population coding, memory-based recognition, and codebooks of prototypes. Unlike the sigmoidal units of some artificial neural networks, the units of MBMs are consistent with the description of cortical neurons. We describe how an example of MBM may be realized in terms of cortical circuitry and biophysical mechanisms, consistent with psychophysical and physiological data.
Subjects
object recognition
IT cortex
view invariance
Persistent DSpace Link
http://hdl.handle.net/1721.1/7217
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.