Counting objects with biologically inspired regulatory-feedback networks

Authors:
Tsvi AchIer;Dervis Can VuraI;Eyal Amir
Affiliations:
Computer Science Department, University of Illinois at Urbana Champaign, Urbana, IL;Physics Department, University of Illinois at Urbana Champaign;Computer Science Department, University of Illinois at Urbana Champaign, Urbana, IL
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 7
Cited 1

A competitive distribution theory of neocortical dynamics

Neural Computation
Convergence of competitive activation models based on virtual lateral inhibition

Neural Networks
A neural model of how the brain represents and compares multi-digit numbers: spatial and categorical processes

Neural Networks
Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning

Neural Computation
A competitive neural model of small number detection

Neural Networks
Input Feedback Networks: Classification and Inference Based on Network Structure

Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
Virtual uteral inhibition in parallel activation models of associative memory

IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 1

Using non-oscillatory dynamics to disambiguate simultaneous patterns

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural networks are relatively successful in recognizing individual patterns. However, when images consist of combination of patterns, a preprocessing step of segmentation is required to avoid combinatorial explosion of the training phase. In practical applications, segmentation is a context dependent task which itself requires recognition. In this paper we propose and develop a biologically inspired neural architecture that can recognize and count an arbitrary collection of objects even if trained with individual objects, without making use of additional segmentation algorithms. The two essential features that govern the neurons in this algorithm are 1. dynamical feedback and 2. competition for activation. We show analytically that while the equations governing the output neurons are highly nonlinear in individual feature amplitudes, they are linear in groups of feature amplitudes. We further demonstrate through simulations, that our architecture can precisely count and recognize scenes in which three and four non-overlapping patterns are presented simultaneously. The ability to generalize numerosity outside the training distribution with a simple learning scheme, lack of connection weights and segmentation algorithms prove regulatory feedback networks not only beneficial for machine learning tasks but also for biological modeling of animal vision.