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
Effects of multiple timescales.Learning error for basic pattern and novel pattern training for variousslow context time constant values are shown. Differences in timescaleare described by the ratio of τ values in thefast and slow context units(τ-slow/τ-fast).Bars in the graph correspond to mean values over 5 learning trials foreach parameter setting. Error bars indicate the degree of standarddeviation. Asterisks indicate significant differences in mean valuesbetween the standard setting(τ-ratio = 14.0)and other settings. The significance of these differences was examinedusing a randomized test. Both in basic pattern training and inadditional training, performance for the case of smallτ-ratio was significantly worse than thestandard setting. These results suggest that multiple timescales in thefast and slow context units was an essential factor leading to theemergence of hierarchical functional differentiation.
© Copyright Policy
Related In: Results  -  Collection

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

pcbi-1000220-g009: Effects of multiple timescales.Learning error for basic pattern and novel pattern training for variousslow context time constant values are shown. Differences in timescaleare described by the ratio of τ values in thefast and slow context units(τ-slow/τ-fast).Bars in the graph correspond to mean values over 5 learning trials foreach parameter setting. Error bars indicate the degree of standarddeviation. Asterisks indicate significant differences in mean valuesbetween the standard setting(τ-ratio = 14.0)and other settings. The significance of these differences was examinedusing a randomized test. Both in basic pattern training and inadditional training, performance for the case of smallτ-ratio was significantly worse than thestandard setting. These results suggest that multiple timescales in thefast and slow context units was an essential factor leading to theemergence of hierarchical functional differentiation.

Mentions: In order to investigate the impact of multiple timescales on hierarchicalfunctional differentiation, performance of the model was tested while changingthe value of the time constant parameter τ in the slowcontext units, while the value of τ in the fast contextunits was held fixed at 5. Difference in timescales was described in terms ofthe ratio of τ values in the fast and slow contextunits (τ-slow/τ-fast). Foreach value of this τ-ratio, five trials were conductedfor both the basic training of five behavior patterns, and for the training ofnovel patterns. Mean values of the learning error for allτ-ratio settings are presented in Figure 9. The significance of differencesbetween the standard setting(τ-ratio = 14.0) andother settings was examined using a randomized test.


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

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

Effects of multiple timescales.Learning error for basic pattern and novel pattern training for variousslow context time constant values are shown. Differences in timescaleare described by the ratio of τ values in thefast and slow context units(τ-slow/τ-fast).Bars in the graph correspond to mean values over 5 learning trials foreach parameter setting. Error bars indicate the degree of standarddeviation. Asterisks indicate significant differences in mean valuesbetween the standard setting(τ-ratio = 14.0)and other settings. The significance of these differences was examinedusing a randomized test. Both in basic pattern training and inadditional training, performance for the case of smallτ-ratio was significantly worse than thestandard setting. These results suggest that multiple timescales in thefast and slow context units was an essential factor leading to theemergence of hierarchical functional differentiation.
© Copyright Policy
Related In: Results  -  Collection

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

pcbi-1000220-g009: Effects of multiple timescales.Learning error for basic pattern and novel pattern training for variousslow context time constant values are shown. Differences in timescaleare described by the ratio of τ values in thefast and slow context units(τ-slow/τ-fast).Bars in the graph correspond to mean values over 5 learning trials foreach parameter setting. Error bars indicate the degree of standarddeviation. Asterisks indicate significant differences in mean valuesbetween the standard setting(τ-ratio = 14.0)and other settings. The significance of these differences was examinedusing a randomized test. Both in basic pattern training and inadditional training, performance for the case of smallτ-ratio was significantly worse than thestandard setting. These results suggest that multiple timescales in thefast and slow context units was an essential factor leading to theemergence of hierarchical functional differentiation.
Mentions: In order to investigate the impact of multiple timescales on hierarchicalfunctional differentiation, performance of the model was tested while changingthe value of the time constant parameter τ in the slowcontext units, while the value of τ in the fast contextunits was held fixed at 5. Difference in timescales was described in terms ofthe ratio of τ values in the fast and slow contextunits (τ-slow/τ-fast). Foreach value of this τ-ratio, five trials were conductedfor both the basic training of five behavior patterns, and for the training ofnovel patterns. Mean values of the learning error for allτ-ratio settings are presented in Figure 9. The significance of differencesbetween the standard setting(τ-ratio = 14.0) andother settings was examined using a randomized test.

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