A dynamic field architecture for the generation of hierarchically organized sequences

Authors:
Boris Durán;Yulia Sandamirskaya;Gregor Schöner
Affiliations:
Interaction Lab, University of Skövde, Skövde, Sweden;Institut für Neuroinformatik, Ruhr-Univesität Bochum, Bochum, Germany;Institut für Neuroinformatik, Ruhr-Univesität Bochum, Bochum, Germany
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Year:
2012

Citing 4
Cited 0

The problem of serial order: a neural network model of sequence learning and recall

Current research in natural language generation
A hierarchical architecture for behavior-based robots

Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 1
Hierarchical dynamical models of motor function

Neurocomputing
An embodied account of serial order: How instabilities drive sequence generation

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A dilemma arises when sequence generation is implemented on embodied autonomous agents. While achieving an individual action goal, the agent must be in a stable state to link to fluctuating and time-varying sensory inputs. To transition to the next goal, the previous state must be released from stability. A previous proposal of a neural dynamics solved this dilemma by inducing an instability when a "condition of satisfaction" signals that an action goal has been reached. The required structure of dynamic coupling limited the complexity and flexibility of sequence generation, however. We address this limitation by showing how the neural dynamics can be generalized to generate hierarchically structured behaviors. Directed couplings downward in the hierarchy initiate chunks of actions, directed couplings upward in the hierarchy signal their termination. We analyze the mathematical mechanisms and demonstrate the flexibility of the scheme in simulation.