Generalisation of action sequences in RNNPB networks with mirror properties

R.H. Cuijpers; F. Stuijt; I. Sprinkhuizen-Kuyper

Generalisation of action sequences in RNNPB networks with mirror properties

R.H. Cuijpers
, F. Stuijt
, I. Sprinkhuizen-Kuyper

Human Technology Interaction

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic

9 Citaten (Scopus)

64 Downloads (Pure)

Samenvatting

The human mirror neuron system (MNS) is supposed to be involved in recognition of observed action sequences. However, it remains unclear how such a system could learn to recognise a large variety of action sequences. Here we investigated a neural network with mirror properties, the Recurrent Neural Network with Parametric Bias (RNNPB). We show that the network is capable of recognising noisy action sequences and that it is capable of generalising from a few learnt examples. Such a mechanism may explain how the human brain is capable of dealing with an infinite variety of action sequences.

Originele taal-2	Engels
Titel	ESANN'2009 proceedings : European Symposium on Artificial Neural Networks
Pagina's	251-256
Status	Gepubliceerd - 2009
Evenement	17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009) - Bruges, België Duur: 22 apr 2009 → 24 apr 2009 Congresnummer: 17

Congres

Congres	17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009)
Verkorte titel	ESANN 2009
Land/Regio	België
Stad	Bruges
Periode	22/04/09 → 24/04/09
Ander	17th European Symposium on Artificial Neural Networks (ESANN2009)

Toegang tot document

Metis233492Definitieve gepubliceerde versie, 680 KB

Citeer dit

@inproceedings{a7e2b07763b549ea8cc622335d8a404c,

title = "Generalisation of action sequences in RNNPB networks with mirror properties",

abstract = "The human mirror neuron system (MNS) is supposed to be involved in recognition of observed action sequences. However, it remains unclear how such a system could learn to recognise a large variety of action sequences. Here we investigated a neural network with mirror properties, the Recurrent Neural Network with Parametric Bias (RNNPB). We show that the network is capable of recognising noisy action sequences and that it is capable of generalising from a few learnt examples. Such a mechanism may explain how the human brain is capable of dealing with an infinite variety of action sequences.",

author = "R.H. Cuijpers and F. Stuijt and I. Sprinkhuizen-Kuyper",

year = "2009",

language = "English",

isbn = "2-930307-09-9",

pages = "251--256",

booktitle = "ESANN'2009 proceedings : European Symposium on Artificial Neural Networks",

note = "17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009), ESANN 2009 ; Conference date: 22-04-2009 Through 24-04-2009",

}

TY - GEN

T1 - Generalisation of action sequences in RNNPB networks with mirror properties

AU - Cuijpers, R.H.

AU - Stuijt, F.

AU - Sprinkhuizen-Kuyper, I.

N1 - Conference code: 17

PY - 2009

Y1 - 2009

N2 - The human mirror neuron system (MNS) is supposed to be involved in recognition of observed action sequences. However, it remains unclear how such a system could learn to recognise a large variety of action sequences. Here we investigated a neural network with mirror properties, the Recurrent Neural Network with Parametric Bias (RNNPB). We show that the network is capable of recognising noisy action sequences and that it is capable of generalising from a few learnt examples. Such a mechanism may explain how the human brain is capable of dealing with an infinite variety of action sequences.

AB - The human mirror neuron system (MNS) is supposed to be involved in recognition of observed action sequences. However, it remains unclear how such a system could learn to recognise a large variety of action sequences. Here we investigated a neural network with mirror properties, the Recurrent Neural Network with Parametric Bias (RNNPB). We show that the network is capable of recognising noisy action sequences and that it is capable of generalising from a few learnt examples. Such a mechanism may explain how the human brain is capable of dealing with an infinite variety of action sequences.

M3 - Conference contribution

SN - 2-930307-09-9

SP - 251

EP - 256

BT - ESANN'2009 proceedings : European Symposium on Artificial Neural Networks

T2 - 17th European Symposium on Artificial Neural Networks Computational Intelligence and Machine Learning (ESANN 2009)

Y2 - 22 April 2009 through 24 April 2009

ER -

Generalisation of action sequences in RNNPB networks with mirror properties

Samenvatting

Congres

Toegang tot document

Vingerafdruk

Citeer dit