TY - JOUR
T1 - Learning to Perceive the World as Probabilistic or Deterministic via Interaction with Others
T2 - A Neuro-Robotics Experiment
AU - Murata, Shingo
AU - Yamashita, Yuichi
AU - Arie, Hiroaki
AU - Ogata, Tetsuya
AU - Sugano, Shigeki
AU - Tani, Jun
N1 - Publisher Copyright:
© 2012 IEEE.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2017/4
Y1 - 2017/4
N2 - We suggest that different behavior generation schemes, such as sensory reflex behavior and intentional proactive behavior, can be developed by a newly proposed dynamic neural network model, named stochastic multiple timescale recurrent neural network (S-MTRNN). The model learns to predict subsequent sensory inputs, generating both their means and their uncertainty levels in terms of variance (or inverse precision) by utilizing its multiple timescale property. This model was employed in robotics learning experiments in which one robot controlled by the S-MTRNN was required to interact with another robot under the condition of uncertainty about the other's behavior. The experimental results show that self-organized and sensory reflex behavior-based on probabilistic prediction-emerges when learning proceeds without a precise specification of initial conditions. In contrast, intentional proactive behavior with deterministic predictions emerges when precise initial conditions are available. The results also showed that, in situations where unanticipated behavior of the other robot was perceived, the behavioral context was revised adequately by adaptation of the internal neural dynamics to respond to sensory inputs during sensory reflex behavior generation. On the other hand, during intentional proactive behavior generation, an error regression scheme by which the internal neural activity was modified in the direction of minimizing prediction errors was needed for adequately revising the behavioral context. These results indicate that two different ways of treating uncertainty about perceptual events in learning, namely, probabilistic modeling and deterministic modeling, contribute to the development of different dynamic neuronal structures governing the two types of behavior generation schemes.
AB - We suggest that different behavior generation schemes, such as sensory reflex behavior and intentional proactive behavior, can be developed by a newly proposed dynamic neural network model, named stochastic multiple timescale recurrent neural network (S-MTRNN). The model learns to predict subsequent sensory inputs, generating both their means and their uncertainty levels in terms of variance (or inverse precision) by utilizing its multiple timescale property. This model was employed in robotics learning experiments in which one robot controlled by the S-MTRNN was required to interact with another robot under the condition of uncertainty about the other's behavior. The experimental results show that self-organized and sensory reflex behavior-based on probabilistic prediction-emerges when learning proceeds without a precise specification of initial conditions. In contrast, intentional proactive behavior with deterministic predictions emerges when precise initial conditions are available. The results also showed that, in situations where unanticipated behavior of the other robot was perceived, the behavioral context was revised adequately by adaptation of the internal neural dynamics to respond to sensory inputs during sensory reflex behavior generation. On the other hand, during intentional proactive behavior generation, an error regression scheme by which the internal neural activity was modified in the direction of minimizing prediction errors was needed for adequately revising the behavioral context. These results indicate that two different ways of treating uncertainty about perceptual events in learning, namely, probabilistic modeling and deterministic modeling, contribute to the development of different dynamic neuronal structures governing the two types of behavior generation schemes.
KW - Generative model
KW - neuro-robotics
KW - precision
KW - prediction error
KW - predictive coding
KW - recurrent neural network (RNN)
UR - http://www.scopus.com/inward/record.url?scp=85027586704&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85027586704&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2015.2492140
DO - 10.1109/TNNLS.2015.2492140
M3 - Article
C2 - 26595928
AN - SCOPUS:85027586704
VL - 28
SP - 830
EP - 848
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
SN - 2162-237X
IS - 4
ER -