« Previous AbstractLactic acid treatment of by-products and phosphorus level in the diet modulate bacterial microbiome and the predicted metagenome functions using the rumen simulation technique    Next AbstractEmpirical relations predicting human and rat tissue:air partition coefficients of volatile organic compounds »

Artif Life

Title:		Ant colony optimization and stochastic gradient descent
Author(s):		Meuleau N; Dorigo M;
Address:		"IRIDIA, Universite Libre de Bruxelles, Avenue Franklin Roosevelt 50, CP 194/6, B-1050 Brussels, Belgium. nmeulau@iridia.ulb.ac.be"
Journal Title:		Artif Life
Year:		2002
Volume:		8
Issue:		2
Page Number:		103 - 121
DOI:		10.1162/106454602320184202
ISSN/ISBN:		1064-5462 (Print) 1064-5462 (Linking)
Abstract:		"In this article, we study the relationship between the two techniques known as ant colony optimization (ACO) and stochastic gradient descent. More precisely, we show that some empirical ACO algorithms approximate stochastic gradient descent in the space of pheromones, and we propose an implementation of stochastic gradient descent that belongs to the family of ACO algorithms. We then use this insight to explore the mutual contributions of the two techniques"
Keywords:		"*Algorithms Animals Ants/physiology Artificial Intelligence *Models, Theoretical Social Behavior *Stochastic Processes;"
Notes:		"MedlineMeuleau, Nicolas Dorigo, Marco eng Research Support, Non-U.S. Gov't 2002/08/13 Artif Life. 2002; 8(2):103-21. doi: 10.1162/106454602320184202"