Abstract


= PDF Reprint,     = BibTeX entry,     = Online Abstract


Click to download PDF version Click to download BibTeX data Clik to view abstract W. S. Grant, L. Itti, Learning Invariant Features in Modulatory Networks through Conflict and Ambiguity, Neural computation, Vol. 31, No. 2, pp. 344-387, MIT Press, 2019. [2018 impact factor: 1.651]

Abstract: This work lays the foundation for a framework of cortical learning based on the idea of a competitive column, which is inspired by the functional organization of neurons in the cortex. A column describes a prototypical organization for neurons that gives rise to an ability to learn scale, rotation, and translation-invariant features. This is empowered by a recently developed learning rule, conflict learning, which enables the network to learn over both driving and modulatory feedforward, feedback, and lateral inputs. The framework is further supported by introducing both a notion of neural ambiguity and an adaptive threshold scheme. Ambiguity, which captures the idea that too many decisions lead to indecision, gives the network a dynamic way to resolve locally ambiguous decisions. The adaptive threshold operates over multiple timescales to regulate neural activity under the varied arrival timings of input in a highly interconnected multilayer network with feedforward and feedback. The competitive column architecture is demonstrated on a large-scale (54,000 neurons and 18 million synapses), invariant model of border ownership. The model is trained on four simple, fixed-scale shapes: two squares, one rectangle, and one symmetric L-shape. Tested on 1899 synthetic shapes of varying scale and complexity, the model correctly assigned border ownership with 74% accuracy. The model's abilities were also illustrated on contours of objects taken from natural images. Combined with conflict learning, the competitive column and ambiguity give a better intuitive understanding of how feedback, modulation, and inhibition may interact in the brain to influence activation and learning.

Themes: Computational Modeling

 

Copyright © 2000-2007 by the University of Southern California, iLab and Prof. Laurent Itti.
This page generated by bibTOhtml on Thu Jan 31 11:39:41 PST 2019