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

Related in: MedlinePlus

Example of behavior sequence for up-down behavior.Proprioception (first row), vision (second row), sparsely encoded RNNactivation (third row), fast and slow context activation (forth andfifth row) of teaching signal (left column), mental simulation oftrained network (center column) and actual sensory feedback in physicalenvironment (right column) during up-down behavior at position 3 areshown. In proprioception, 4 out of a total of 8 dimensions were plotted(full line: left arm pronation, dashed: left elbow flexion,dot-dash-dot-dash: right shoulder flexion, dotted: right arm pronation).In the case of vision, two lines correspond to the relative position ofthe object (full line: X-axis, dashed line: Y-axis). Values forproprioception and vision were mapped to the range from 0.0 to 1.0.CTRNN outputs are sparsely encoded. Both in CTRNN outputs and contextactivation, the y axis of the graph corresponds to each unit from amongthe output units and context units. A long sideways rectangle thusindicates the activity of a single neuron over many time steps. Thefirst 64 units of output correspond to proprioception and the last 36units of output correspond to vision. Colors of rectangles indicateactivation level, as indicated in the color bar at the lower right.Reach: reach for the object, UD: up-down, Home: return to the homeposition.
© Copyright Policy
Related In: Results  -  Collection

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

pcbi-1000220-g004: Example of behavior sequence for up-down behavior.Proprioception (first row), vision (second row), sparsely encoded RNNactivation (third row), fast and slow context activation (forth andfifth row) of teaching signal (left column), mental simulation oftrained network (center column) and actual sensory feedback in physicalenvironment (right column) during up-down behavior at position 3 areshown. In proprioception, 4 out of a total of 8 dimensions were plotted(full line: left arm pronation, dashed: left elbow flexion,dot-dash-dot-dash: right shoulder flexion, dotted: right arm pronation).In the case of vision, two lines correspond to the relative position ofthe object (full line: X-axis, dashed line: Y-axis). Values forproprioception and vision were mapped to the range from 0.0 to 1.0.CTRNN outputs are sparsely encoded. Both in CTRNN outputs and contextactivation, the y axis of the graph corresponds to each unit from amongthe output units and context units. A long sideways rectangle thusindicates the activity of a single neuron over many time steps. Thefirst 64 units of output correspond to proprioception and the last 36units of output correspond to vision. Colors of rectangles indicateactivation level, as indicated in the color bar at the lower right.Reach: reach for the object, UD: up-down, Home: return to the homeposition.

Mentions: Figure 4 and Figure 5 illustrate examplesof sensori-motor sequences, as well as examples of teaching signals and trainedmodel network interacting with a physical environment through the body of therobot. Figure 4 alsoincludes examples sequences generated by mental simulation. Both in mentalsimulation and in the context of the robot interacting with a physicalenvironment, the trained network reproduced target behavior sequencesuccessfully.


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

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

Example of behavior sequence for up-down behavior.Proprioception (first row), vision (second row), sparsely encoded RNNactivation (third row), fast and slow context activation (forth andfifth row) of teaching signal (left column), mental simulation oftrained network (center column) and actual sensory feedback in physicalenvironment (right column) during up-down behavior at position 3 areshown. In proprioception, 4 out of a total of 8 dimensions were plotted(full line: left arm pronation, dashed: left elbow flexion,dot-dash-dot-dash: right shoulder flexion, dotted: right arm pronation).In the case of vision, two lines correspond to the relative position ofthe object (full line: X-axis, dashed line: Y-axis). Values forproprioception and vision were mapped to the range from 0.0 to 1.0.CTRNN outputs are sparsely encoded. Both in CTRNN outputs and contextactivation, the y axis of the graph corresponds to each unit from amongthe output units and context units. A long sideways rectangle thusindicates the activity of a single neuron over many time steps. Thefirst 64 units of output correspond to proprioception and the last 36units of output correspond to vision. Colors of rectangles indicateactivation level, as indicated in the color bar at the lower right.Reach: reach for the object, UD: up-down, Home: return to the homeposition.
© Copyright Policy
Related In: Results  -  Collection

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

pcbi-1000220-g004: Example of behavior sequence for up-down behavior.Proprioception (first row), vision (second row), sparsely encoded RNNactivation (third row), fast and slow context activation (forth andfifth row) of teaching signal (left column), mental simulation oftrained network (center column) and actual sensory feedback in physicalenvironment (right column) during up-down behavior at position 3 areshown. In proprioception, 4 out of a total of 8 dimensions were plotted(full line: left arm pronation, dashed: left elbow flexion,dot-dash-dot-dash: right shoulder flexion, dotted: right arm pronation).In the case of vision, two lines correspond to the relative position ofthe object (full line: X-axis, dashed line: Y-axis). Values forproprioception and vision were mapped to the range from 0.0 to 1.0.CTRNN outputs are sparsely encoded. Both in CTRNN outputs and contextactivation, the y axis of the graph corresponds to each unit from amongthe output units and context units. A long sideways rectangle thusindicates the activity of a single neuron over many time steps. Thefirst 64 units of output correspond to proprioception and the last 36units of output correspond to vision. Colors of rectangles indicateactivation level, as indicated in the color bar at the lower right.Reach: reach for the object, UD: up-down, Home: return to the homeposition.
Mentions: Figure 4 and Figure 5 illustrate examplesof sensori-motor sequences, as well as examples of teaching signals and trainedmodel network interacting with a physical environment through the body of therobot. Figure 4 alsoincludes examples sequences generated by mental simulation. Both in mentalsimulation and in the context of the robot interacting with a physicalenvironment, the trained network reproduced target behavior sequencesuccessfully.

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
Related in: MedlinePlus