Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot Experiment
Возникновение функциональной иерархии в нейросетевой модели с несколькими временными масштабами: эксперимент с гуманоидным роботом
2008-11-06
SCID: 54.1/kbbgjm2f
Discuss with AI
functional hierarchyhumanoid robot controlmotor primitivesmultiple timescales neural networksensori-motor sequence segmentation
Figures from the paper
Abstract (AI)
It is generally thought that skilled behavior in human beings results from a functional hierarchy of the motor control system, within which reusable motor primitives are flexibly integrated into various sensori-motor sequence patterns. The underlying neural mechanisms governing the way in which continuous sensori-motor flows are segmented into primitives and the way in which series of primitives are integrated into various behavior sequences have, however, not yet been clarified. In earlier studies, this functional hierarchy has been realized through the use of explicit hierarchical structure, with local modules representing motor primitives in the lower level and a higher module representing sequences of primitives switched via additional mechanisms such as gate-selecting. When sequences contain similarities and overlap, however, a conflict arises in such earlier models between generalization and segmentation, induced by this separated modular structure. To address this issue, we propose a different type of neural network model. The current model neither makes use of separate local modules to represent primitives nor introduces explicit hierarchical structure. Rather than forcing architectural hierarchy onto the system, functional hierarchy emerges through a form of self-organization that is based on two distinct types of neurons, each with different time properties ("multiple timescales"). Through the introduction of multiple timescales, continuous sequences of behavior are segmented into reusable primitives, and the primitives, in turn, are flexibly integrated into novel sequences. In experiments, the proposed network model, coordinating the physical body of a humanoid robot through high-dimensional sensori-motor control, also successfully situated itself within a physical environment. Our results suggest that it is not only the spatial connections between neurons but also the timescales of neural activity that act as important mechanisms leading to functional hierarchy in neural systems.
Key Findings
1
A neural network with multiple neuronal timescales develops functional hierarchy without explicit hierarchical architecture or separate primitive modules.
2
Distinct neuronal time properties enable continuous sensorimotor streams to be segmented into reusable motor primitives.
3
The findings suggest that neural activity timescales, alongside spatial connectivity, are important mechanisms underlying functional hierarchy.
4
The model successfully controlled a humanoid robot with high-dimensional sensorimotor dynamics and enabled it to situate itself within a physical environment.
5
The self-organized primitives can be flexibly recombined into novel behavioral sequences, addressing conflicts between generalization and segmentation in modular models.
Research Object
A multiple-timescale neural network model controlling a humanoid robot in a physical environment
Research Subject
Emergent functional hierarchy for segmenting continuous sensorimotor behavior into reusable motor primitives and flexibly integrating them into novel sequences
Publication Details
Publication Date
2008-11-06
Journal
Publisher
ISSN
Cited by
484
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest