DocumentCode :
186286
Title :
Sensori-motor networks vs neural networks for visual stimulus prediction
Author :
Santos, Ricardo ; Ferreira, Ricardo ; Cardoso, Alberto ; Bernardino, Alexandre
Author_Institution :
Inst. for Syst. & Robot., Inst. Super. Tecnico, Lisbon, Portugal
fYear :
2014
fDate :
13-16 Oct. 2014
Firstpage :
287
Lastpage :
292
Abstract :
This paper focuses on a recently developed special type of biologically inspired architecture, which we denote as a sensori-motor network, able to co-develop sensori-motor structures directly from the data acquired by a robot interacting with its environment. Such networks learn efficient internal models of the sensori-motor system, developing simultaneously sensor and motor representations (receptive fields) adapted to the robot and surrounding environment. In this paper we compare this sensori-motor network with a conventional neural network in the ability to create efficient predictors of visuomotor relationships. We confirm that the sensori-motor network is significantly more efficient in terms of required computations and is more precise (less prediction error) than the linear neural network in predicting self induced visual stimuli.
Keywords :
control engineering computing; data acquisition; human-robot interaction; neural net architecture; robot vision; visual perception; biologically inspired architecture; data acquisition; linear neural network; neural networks; robot interaction; self induced visual stimuli; sensor and motor representation; sensorimotor networks; sensorimotor structures; visual stimulus prediction; visuomotor relationship; Artificial neural networks; Image reconstruction; Optimization; Organizations; Robot sensing systems; Visualization; Stimulus prediction; neural networks; sensori-motor maps; visual and motor receptive fields;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Development and Learning and Epigenetic Robotics (ICDL-Epirob), 2014 Joint IEEE International Conferences on
Conference_Location :
Genoa
Type :
conf
DOI :
10.1109/DEVLRN.2014.6982995
Filename :
6982995
Link To Document :
بازگشت