Observations on Cortical Mechanisms for Object Recognition and Learning

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 tem-is of cortical circuitry and biophysical mechanisms, consistent with psychophysical and physiological data. Object recognition, IT cortex, View invariance.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1993
Accession Number
ADA276800

Entities

People

  • Anya Hurlbert
  • Tomaso Poggio

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Autonomy

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Brain
  • Cognitive Science
  • Computer Languages
  • Computer Vision
  • Databases
  • Detectors
  • Information Processing
  • Information Systems
  • Military Research
  • Neurosciences
  • Object Recognition
  • Observation
  • Recognition
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Neural Network Machine Learning.
  • Neuroscience

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Biotechnology