Limits...
Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment.

Yamashita Y, Tani J - PLoS Comput. Biol. (2008)

Bottom Line: The current model neither makes use of separate local modules to represent primitives nor introduces explicit hierarchical structure.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.

View Article: PubMed Central - PubMed

Affiliation: Laboratory for Behavior and Dynamic Cognition, RIKEN Brain Science Institute, Wako-shi, Saitama, Japan. yamay@brain.riken.jp

ABSTRACT
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.

Show MeSH
Changes in context state space associated with changes in objectposition.Changes of context activation during each behavior at every position areshown in a 2 dimensional space based on the results of PCA analysis. Thefour graphs on the left side and single graph on the right sidecorrespond to fast context activities and slow context activities,respectively. State changes of the fast context units for each behaviorexhibit a particular structure which shifts with the object position. Onthe other hand, activity of the slow context units for a particularbehavioral task exhibited very little location-dependent variation. UD:up-down, LR: left-right, BF: backward-forward and Touch: touch withsingle hand.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2570613&req=5

pcbi-1000220-g006: Changes in context state space associated with changes in objectposition.Changes of context activation during each behavior at every position areshown in a 2 dimensional space based on the results of PCA analysis. Thefour graphs on the left side and single graph on the right sidecorrespond to fast context activities and slow context activities,respectively. State changes of the fast context units for each behaviorexhibit a particular structure which shifts with the object position. Onthe other hand, activity of the slow context units for a particularbehavioral task exhibited very little location-dependent variation. UD:up-down, LR: left-right, BF: backward-forward and Touch: touch withsingle hand.

Mentions: In order to visualize changes of state in the network during execution ofbehavioral tasks, two principal components of context unit activation valueswere plotted in Figure 6 forevery behavior and at every position. The clapping hand behavior was not plottedas this behavior was independent of object position.


Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment.

Yamashita Y, Tani J - PLoS Comput. Biol. (2008)

Changes in context state space associated with changes in objectposition.Changes of context activation during each behavior at every position areshown in a 2 dimensional space based on the results of PCA analysis. Thefour graphs on the left side and single graph on the right sidecorrespond to fast context activities and slow context activities,respectively. State changes of the fast context units for each behaviorexhibit a particular structure which shifts with the object position. Onthe other hand, activity of the slow context units for a particularbehavioral task exhibited very little location-dependent variation. UD:up-down, LR: left-right, BF: backward-forward and Touch: touch withsingle hand.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2570613&req=5

pcbi-1000220-g006: Changes in context state space associated with changes in objectposition.Changes of context activation during each behavior at every position areshown in a 2 dimensional space based on the results of PCA analysis. Thefour graphs on the left side and single graph on the right sidecorrespond to fast context activities and slow context activities,respectively. State changes of the fast context units for each behaviorexhibit a particular structure which shifts with the object position. Onthe other hand, activity of the slow context units for a particularbehavioral task exhibited very little location-dependent variation. UD:up-down, LR: left-right, BF: backward-forward and Touch: touch withsingle hand.
Mentions: In order to visualize changes of state in the network during execution ofbehavioral tasks, two principal components of context unit activation valueswere plotted in Figure 6 forevery behavior and at every position. The clapping hand behavior was not plottedas this behavior was independent of object position.

Bottom Line: The current model neither makes use of separate local modules to represent primitives nor introduces explicit hierarchical structure.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.

View Article: PubMed Central - PubMed

Affiliation: Laboratory for Behavior and Dynamic Cognition, RIKEN Brain Science Institute, Wako-shi, Saitama, Japan. yamay@brain.riken.jp

ABSTRACT
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.

Show MeSH