Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot Experiment

By Yuichi Yamashita, Jun Tani. PLoS Comput. Biol., 2008

507 citations recorded by the source corpus.

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.

Subfields: Cognitive Neuroscience, Social Psychology

View Paper: https://www.semanticscholar.org/paper/2907fc4feb076f20604d7181504221ca748d2075

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Social Psychology

Citations in the corpus

Morphological change in machines accelerates the evolution of robust behavior (2011, background): “Robustness can arise as a result of modularity (23), but no increased structural (24) or functional (25) modularity was detected in the controllers evolved within the morphologically changing A B”
Seamless Integration and Coordination of Cognitive Skills in Humanoid Robots: A Deep Learning Approach (2017, background): “an ability to recognize dynamic visual scenes [17], and the MTRNN to learn compositional actions [18].”
Self-Organization of Spatio-Temporal Hierarchy via Learning of Dynamic Visual Image Patterns on Action Sequences (2015, background): “…a spatial hierarchy through the learning of static visual image patterns seen in the CNN [6], and the other is the self-organization of a temporal hierarchy through the learning of dynamic patterns such as sensory-motor sequences seen in a multiple timescales recurrent neural network (MTRNN) [16].”
A Hierarchical Recurrent Neural Network for Symbolic Melody Generation (2017, background): “The Multiple Timescale Recurrent Neural Network (MTRNN) realizes the self-organization of a functional hierarchy with two types of neurons “fast” unit and “slow” unit [14].”
Thinking fast and slow: Optimization decomposition across timescales (2017, background): “Even human sensorimotor control exhibits the same phenomenon, with slow timescale behaviors such as trajectory planning and fast timescale behaviors such as involuntary reflexes [19], [31], [42], [46].”
Neural and Computational Mechanisms of Action Processing: Interaction between Visual and Motor Representations. (2015, methodology): “More recently, such models have been extended by inclusion of neuron pools with multiple timescales, forming a hierarchy (Yamashita and Tani, 2008).”