Goal-seeking behavior in a connectionist model

被引:7
作者
Portegys, TE [1 ]
机构
[1] Lucent Technol, Naperville, IL 60566 USA
关键词
computational neuroethology; connectionism; goal-seeking; neural networks;
D O I
10.1023/A:1011970925799
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Goal-seeking behavior in a connectionist model is demonstrated using the examples of foraging by a simulated ant and cooperative nest-building by a pair of simulated birds. The model, a control neural network, translates needs into responses. The purpose of this work is to produce lifelike behavior with a goal-seeking artificial neural network. The foraging ant example illustrates the intermediation of neurons to guide the ant to a goal in a semi-predictable environment. In the nest-building example, both birds, executing gender-specific networks, exhibit social nesting and feeding behavior directed toward multiple goals.
引用
收藏
页码:225 / 253
页数:29
相关论文
共 27 条
[1]   MECHANISMS OF PLANNING AND PROBLEM-SOLVING IN THE BRAIN [J].
ALBUS, JS .
MATHEMATICAL BIOSCIENCES, 1979, 45 (3-4) :247-293
[2]  
ANDERSON C, 1997, 4 EUR C ART LIF CAMB
[3]   Swarm smarts [J].
Bonabeau, E ;
Théraulaz, G .
SCIENTIFIC AMERICAN, 2000, 282 (03) :72-79
[4]  
Bonabeau E, 1999, SWARM INTELLIGENCE N
[5]  
DROGOUL A, 1993, ANIMALS ANIMATS, V2
[6]  
Dudai Y., 1989, NEUROBIOLOGY MEMORY
[7]  
Fu L, 1994, NEURAL NETWORKS COMP
[8]  
GOSS S, 1992, PRACTICE AUTONOMOUS
[9]  
HAMPSON SE, 1990, CONNECTIONIST PROBLE
[10]  
HOLMES W, 1992, SINGLE NEURON COMPUT