Inference of other's internal neural models from active observation

Kyung Joong Kim, Sung-Bae Cho

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Recently, there have been several attempts to replicate theory of mind, which explains how humans infer the mental states of other people using multiple sensory input, with artificial systems. One example of this is a robot that observes the behavior of other artificial systems and infers their internal models, mapping sensory inputs to the actuator's control signals. In this paper, we present the internal model as an artificial neural network, similar to biological systems. During inference, an observer can use an active incremental learning algorithm to guess an actor's internal neural model. This could significantly reduce the effort needed to guess other people's internal models. We apply an algorithm to the actor-observer robot scenarios with/without prior knowledge of the internal models. To validate our approach, we use a physics-based simulator with virtual robots. A series of experiments reveal that the observer robot can construct an "other's self-model", validating the possibility that a neural-based approach can be used as a platform for learning cognitive functions.

Original languageEnglish
Pages (from-to)37-47
Number of pages11
JournalBioSystems
Volume128
DOIs
Publication statusPublished - 2015 Feb 1

Fingerprint

Observation
Internal
Theory of Mind
Problem-Based Learning
Physics
Robot
Robots
Cognition
Observer
Learning
Guess
Model
Incremental Algorithm
Incremental Learning
Active Learning
Signal Control
Biological systems
Prior Knowledge
Biological Systems
Learning algorithms

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modelling and Simulation
  • Biochemistry, Genetics and Molecular Biology(all)
  • Applied Mathematics

Cite this

@article{013fef05f1db4f3dbfbf7beac5922e60,
title = "Inference of other's internal neural models from active observation",
abstract = "Recently, there have been several attempts to replicate theory of mind, which explains how humans infer the mental states of other people using multiple sensory input, with artificial systems. One example of this is a robot that observes the behavior of other artificial systems and infers their internal models, mapping sensory inputs to the actuator's control signals. In this paper, we present the internal model as an artificial neural network, similar to biological systems. During inference, an observer can use an active incremental learning algorithm to guess an actor's internal neural model. This could significantly reduce the effort needed to guess other people's internal models. We apply an algorithm to the actor-observer robot scenarios with/without prior knowledge of the internal models. To validate our approach, we use a physics-based simulator with virtual robots. A series of experiments reveal that the observer robot can construct an {"}other's self-model{"}, validating the possibility that a neural-based approach can be used as a platform for learning cognitive functions.",
author = "Kim, {Kyung Joong} and Sung-Bae Cho",
year = "2015",
month = "2",
day = "1",
doi = "10.1016/j.biosystems.2015.01.005",
language = "English",
volume = "128",
pages = "37--47",
journal = "BioSystems",
issn = "0303-2647",
publisher = "Elsevier Ireland Ltd",

}

Inference of other's internal neural models from active observation. / Kim, Kyung Joong; Cho, Sung-Bae.

In: BioSystems, Vol. 128, 01.02.2015, p. 37-47.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Inference of other's internal neural models from active observation

AU - Kim, Kyung Joong

AU - Cho, Sung-Bae

PY - 2015/2/1

Y1 - 2015/2/1

N2 - Recently, there have been several attempts to replicate theory of mind, which explains how humans infer the mental states of other people using multiple sensory input, with artificial systems. One example of this is a robot that observes the behavior of other artificial systems and infers their internal models, mapping sensory inputs to the actuator's control signals. In this paper, we present the internal model as an artificial neural network, similar to biological systems. During inference, an observer can use an active incremental learning algorithm to guess an actor's internal neural model. This could significantly reduce the effort needed to guess other people's internal models. We apply an algorithm to the actor-observer robot scenarios with/without prior knowledge of the internal models. To validate our approach, we use a physics-based simulator with virtual robots. A series of experiments reveal that the observer robot can construct an "other's self-model", validating the possibility that a neural-based approach can be used as a platform for learning cognitive functions.

AB - Recently, there have been several attempts to replicate theory of mind, which explains how humans infer the mental states of other people using multiple sensory input, with artificial systems. One example of this is a robot that observes the behavior of other artificial systems and infers their internal models, mapping sensory inputs to the actuator's control signals. In this paper, we present the internal model as an artificial neural network, similar to biological systems. During inference, an observer can use an active incremental learning algorithm to guess an actor's internal neural model. This could significantly reduce the effort needed to guess other people's internal models. We apply an algorithm to the actor-observer robot scenarios with/without prior knowledge of the internal models. To validate our approach, we use a physics-based simulator with virtual robots. A series of experiments reveal that the observer robot can construct an "other's self-model", validating the possibility that a neural-based approach can be used as a platform for learning cognitive functions.

UR - http://www.scopus.com/inward/record.url?scp=84921986495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921986495&partnerID=8YFLogxK

U2 - 10.1016/j.biosystems.2015.01.005

DO - 10.1016/j.biosystems.2015.01.005

M3 - Article

C2 - 25617791

AN - SCOPUS:84921986495

VL - 128

SP - 37

EP - 47

JO - BioSystems

JF - BioSystems

SN - 0303-2647

ER -