Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems.
Abstract
This paper describes how agents can learn an internal model of the world structurally by focusing on the problem of behavior-based articulation. We develop an on-line learning scheme-the so-called mixture of recurrent neural net (RNN) experts-in which a set of RNN modules become self-organized as experts on multiple levels, in order to account for the different categories of sensory-motor flow which the robot experiences. Autonomous switching of activated modules in the lower level actually represents the articulation of the sensory-motor flow. In the meantime, a set of RNNs in the higher level competes to learn the sequences of module switching in the lower level, by which articulation at a further, more abstract level can be achieved. The proposed scheme was examined through simulation experiments involving the navigation learning problem. Our dynamical system analysis clarified the mechanism of the articulation. The possible correspondence between the articulation mechanism and the attention switching mechanism in thalamo-cortical loops is also discussed.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The Active Inference scheme for adaptive control connects well with hierarchical and layered robotic control architectures, where higher levels encode goal-directed controllers or schemas that contextualize lower-level reflex or habit-like control loops.
“The Active Inference scheme for adaptive control connects well with hierarchical and layered robotic control architectures (Arbib, 1992, Brooks, 1991, Tani and Nolfi, 1999, Verschure et al., 2003), where higher levels encode goal-directed controllers or schemas that contextualize lower-level reflex or habit-like control loops.”
From Active Inference, homeostatic regulation and adaptive behavioural control (2015) · cites this paper as Tani and Nolfi, 1999
Cites
McClelland, J. L., Rumelhart, D. E., & AU (1987) · doi:10.7551/mitpress/5237.001.0001 · Cited by 3,315 · see citing works
The Embodied Mind: Cognitive Science and Human Experience
Varela, F. J., Thompson, E., & Rosch, E. (2017) · doi:10.7551/mitpress/9780262529365.001.0001 · Cited by 2,449 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Intrinsic Motivation Systems for Autonomous Mental Development
Oudeyer, P.-Y., Kaplan, F., & Hafner, V. V. (2007) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2006.890271 · Cited by 1,126 · see citing works
Active inference and epistemic value
Friston, K., Rigoli, F., Ognibene, D., Mathys, C., Fitzgerald, T., & Pezzulo, G. (2015) · Cognitive Neuroscience · doi:10.1080/17588928.2015.1020053 · Cited by 731 · see citing works
Active Inference, homeostatic regulation and adaptive behavioural control
Pezzulo, G., Rigoli, F., & Friston, K. (2015) · Progress in Neurobiology · doi:10.1016/j.pneurobio.2015.09.001 · Cited by 650 · see citing works
“The Active Inference scheme for adaptive control connects well with hierarchical and layered robotic control architectures (Arbib, 1992; Brooks, 1991; Tani and Nolfi, 1999; Verschure et al., 2003), where higher levels encode goal-directed controllers or schemas that contextualize lower-level reflex or habit-like contr…”
Dynamical approaches to cognitive science
Beer, R. D. (2000) · Trends in Cognitive Sciences · doi:10.1016/s1364-6613(99)01440-0 · Cited by 639 · see citing works
Multiple model-based reinforcement learning
Doya, K., Samejima, K., Katagiri, K.-I., & Kawato, M. (2002) · Neural Computation · doi:10.1162/089976602753712972 · Cited by 476 · see citing works
Symbol emergence in robotics: a survey
Taniguchi, T., Nagai, T., Nakamura, T., Iwahashi, N., Ogata, T., & Asoh, H. (2016) · Advanced Robotics · doi:10.1080/01691864.2016.1164622 · Cited by 150 · see citing works
Hierarchical MOSAIC for movement generation.
Haruno, M., Wolpert, D. M., & Kawato, M. (2003) · International Congress Series · doi:10.1016/s0531-5131(03)00190-0 · Cited by 132 · see citing works
Predictive processing in cognitive robotics: A review
Ciria, A., Schillaci, G., Pezzulo, G., Hafner, V. V., & Lara, B. (2021) · Neural Computation · doi:10.1162/neco_a_01383 · Cited by 51 · see citing works
Yurtsever, E., Yamazaki, S., Miyajima, C., Takeda, K., Mori, M., Hitomi, K., & Egawa, M. (2018) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2018.2843171 · Cited by 30 · see citing works
Cohen, D., van Swinderen, B., & Tsuchiya, N. (2018) · eneuro · doi:10.1523/eneuro.0329-17.2018 · Cited by 23 · see citing works
Ando, T., Robotics and Design for Innovative Healthcare, G. S. O. M., Watanabe, M., Nishimoto, K., Matsumoto, Y., Seki, M., Fujie, M. G., & Graduate School of Creative Science and Engineering, F. O. S. A. E. (2012) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2012.p0141 · Cited by 27 · see citing works
- Authors
- Tani, J., & Nolfi, S.
- Affiliations
- Sony Computer Science Laboratories (JP)
- National Research Council (IT)
- Corresponding author
- Tani, J.
- Venue
- Neural Networks
- Publisher
- Elsevier BV
- Published
- 1999-10
- Volume
- 12
- Issue
- 7-8
- Pages
- 1131-1141
- ISSN
- 0893-6080 (ISSN-L)
- OpenAlex
- W133237934
- Cited by
- 259
- References
- 2
- Citations by year
- 2026: 1 · 2025: 7 · 2024: 4 · 2023: 5 · 2022: 3 · 2021: 6 · 2020: 7 · 2019: 6 · 2018: 4 · 2017: 9 · 2016: 7 · 2015: 9 · 2014: 5 · 2013: 6 · 2012: 6
- FWCI
- 7.93
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Neural Networks (publishedVersion)
- The MIT Press eBooks (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Embodied and Extended Cognition
- Keywords
- hierarchical learning, recurrent neural networks, self-organization, dynamical systems analysis, attentional shift, thalamocortical loop, online learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
