Object recognition and sensitive periods: A computational analysis of visual imprinting

Authors:
Randall C. O'Reilly;Mark H. Johnson
Affiliations:
Department of Psychology, Carnegie Mellon University, Pittsburgh, PA 15213 USA;Department of Psychology, Carnegie Mellon University, Pittsburgh, PA 15213 USA
Venue:
Neural Computation
Year:
1994

Citing 6
Cited 3

Computational vision and regularization theory

Nature
Feature discovery by competitive learning

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning invariance from transformation sequences

Neural Computation
Synchronization of bursting action potential discharge in a model network of neocortical neurons

Neural Computation
Review:

Neural Computation
A canonical microcircuit for neocortex

Neural Computation

Information maximization in face processing

Neurocomputing
Incremental slow feature analysis: Adaptive low-complexity slow feature updating from high-dimensional input streams

Neural Computation
Fractal analogies for general intelligence

AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Using neural and behavioral constraints from a relatively simple biological visual system, we evaluate the mechanism and behavioral implications of a model of invariant object recognition. Evidence from a variety of methods suggests that a localized portion of the domestic chick brain, the intermediate and medial hyperstriatum ventrale (IMHV), is critical for object recognition. We have developed a neural network model of translation-invariant object recognition that incorporates features of the neural circuitry of IMHV, and exhibits behavior qualitatively similar to a range of findings in the filial imprinting paradigm. We derive several counter-intuitive behavioral predictions that depend critically upon the biologically derived features of the model. In particular, we propose that the recurrent excitatory and lateral inhibitory circuitry in the model, and observed in IMHV, produces hysteresis on the activation state of the units in the model and the principal excitatory neurons in IMHV. Hysteresis, when combined with a simple Hebbian covariance learning mechanism, has been shown in this and earlier work (Földiák 1991; O'Reilly and McClelland 1992) to produce translation-invariant visual representations. The hysteresis and learning rule are responsible for a sensitive period phenomenon in the network, and for a series of novel temporal blending phenomena. These effects are empirically testable. Further, physiological and anatomical features of mammalian visual cortex support a hysteresis-based mechanism, arguing for the generality of the algorithm.