Some adaptive advantages of the ability to make predictions

Authors:
Daniele Caligiore;Massimo Tria;Domenico Parisi
Affiliations:
Institute of Cognitive Sciences and Technologies, National Research Council, Rome, Italy;Institute of Cognitive Sciences and Technologies, National Research Council, Rome, Italy;Institute of Cognitive Sciences and Technologies, National Research Council, Rome, Italy
Venue:
SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior
Year:
2006

Citing 3
Cited 0

Learning and evolution in neural networks

Adaptive Behavior
Towards a cognitive robotics

Adaptive Behavior
Learning to Predict by the Methods of Temporal Differences

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe some simple simulations showing two possible adaptive advantages of the ability to predict the consequences of one's actions: predicted inputs can replace missing inputs and predicted success vs failure can help deciding whether to actually executing a planned action or not The neural networks controlling the organisms' behaviour include distinct modules whose connection weights are all genetically inherited and evolved using a genetic algorithm except those of the predictive module which are learned during life.