Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition

Abstract

Experiments are described with a versatile pictorial prototype based learning scheme for 3D object recognition. The GRBF scheme seems to be amenable to realization in biophysical hardware because the only kind of computation it involves can be effectively carried out by combining receptive fields. Furthermore, the scheme is computationally attractive because it brings together the old notion of a grandmother cell and the rigorous approximation methods of regularization and splines. Keywords: Object recognition, Representation, Nonlinear interpolation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1990
Accession Number
ADA225514

Entities

People

  • Shimon Edelman
  • Tomaso Poggio

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Anti-Virus Software
  • Coding
  • Computer Vision
  • Computers
  • Coordinate Systems
  • Dimensionality Reduction
  • Information Processing
  • Interpolation
  • Machine Learning
  • Object Recognition
  • Probability
  • Psychology
  • Random Walk
  • Recognition
  • Three Dimensional
  • Two Dimensional
  • Vector Spaces

Readers

  • Approximation Theory.
  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • Biotechnology