CaltechTHESIS
  A Caltech Library Service

Neural Routing Circuits for Forming Invariant Representations of Visual Objects

Citation

Olshausen, Bruno Adolphus (1994) Neural Routing Circuits for Forming Invariant Representations of Visual Objects. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/PSR1-YH20. https://resolver.caltech.edu/CaltechTHESIS:04162013-161719346

Abstract

This thesis presents a biologically plausible model of an attentional mechanism for forming position- and scale-invariant representations of objects in the visual world. The model relies on a set of control neurons to dynamically modify the synaptic strengths of intra-cortical connections so that information from a windowed region of primary visual cortex (Vl) is selectively routed to higher cortical areas. Local spatial relationships (i.e., topography) within the attentional window are preserved as information is routed through the cortex, thus enabling attended objects to be represented in higher cortical areas within an object-centered reference frame that is position and scale invariant. The representation in V1 is modeled as a multiscale stack of sample nodes with progressively lower resolution at higher eccentricities. Large changes in the size of the attentional window are accomplished by switching between different levels of the multiscale stack, while positional shifts and small changes in scale are accomplished by translating and rescaling the window within a single level of the stack. The control signals for setting the position and size of the attentional window are hypothesized to originate from neurons in the pulvinar and in the deep layers of visual cortex. The dynamics of these control neurons are governed by simple differential equations that can be realized by neurobiologically plausible circuits. In pre-attentive mode, the control neurons receive their input from a low-level "saliency map" representing potentially interesting regions of a scene. During the pattern recognition phase, control neurons are driven by the interaction between top-down (memory) and bottom-up (retinal input) sources. The model respects key neurophysiological, neuroanatomical, and psychophysical data relating to attention, and it makes a variety of experimentally testable predictions.

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:vision, object recognition, invariance, dynamic routing, neural networks, attention
Degree Grantor:California Institute of Technology
Division:Biology
Major Option:Computation and Neural Systems
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Anderson, Charles Hammond (advisor)
  • Van Essen, David (advisor)
Thesis Committee:
  • Van Essen, David (chair)
  • Anderson, Charles Hammond
  • Perona, Pietro
  • Koch, Christof
Defense Date:27 January 1994
Non-Caltech Author Email:baolshausen (AT) berkeley.edu
Record Number:CaltechTHESIS:04162013-161719346
Persistent URL:https://resolver.caltech.edu/CaltechTHESIS:04162013-161719346
DOI:10.7907/PSR1-YH20
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:7617
Collection:CaltechTHESIS
Deposited By: John Wade
Deposited On:17 Apr 2013 22:14
Last Modified:21 Dec 2019 02:53

Thesis Files

[img]
Preview
PDF - Final Version
See Usage Policy.

27MB

Repository Staff Only: item control page