Learning Complex Population-Coded Sequences

Authors:
Kiran V. Byadarhaly;Mithun Perdoor;Suresh Vasa;Emmanuel Fernandez;Ali A. Minai
Affiliations:
Department of Electrical & Computer Engineering, University of Cincinnati, Cincinnati 45221-0030;Department of Electrical & Computer Engineering, University of Cincinnati, Cincinnati 45221-0030;Department of Electrical & Computer Engineering, University of Cincinnati, Cincinnati 45221-0030;Department of Electrical & Computer Engineering, University of Cincinnati, Cincinnati 45221-0030;Department of Electrical & Computer Engineering, University of Cincinnati, Cincinnati 45221-0030
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Year:
2009

Citing 10
Cited 1

Storing temporal sequences

Neural Networks
A neural network for coding of trajectories by time series of neuronal population vectors

Neural Computation
A neural network model for temporal sequence learning and motor programming

Neural Networks
What are the computations of the cerebellum, the basal ganglia and the cerebral cortex?

Neural Networks - Special issue on organisation of computation in brain-like systems
Hard-wired models of working memory and temporal sequence storage and generation

Neural Networks
A neural model of cortico-cerebellar interactions during attentive imitation and predictive learning of sequential handwriting movements

Neural Networks - Special issue on the global brain: imaging and modelling
Sequence Learning - Paradigms, Algorithms, and Applications

Sequence Learning - Paradigms, Algorithms, and Applications
Agents of the mind

Biological Cybernetics
Stable-yet-switchable (SyS) attractor networks

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
A dynamical connectionist model of idea generation

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks

2012 Special Issue: A modular neural model of motor synergies

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In humans and primates, the sequential structure of complex actions is apparently learned at an abstract "cognitive" level in several regions of the frontal cortex, independent of the control of the immediate effectors by the motor system. At this level, actions are represented in terms of kinematic parameters --- especially direction of end effector movement --- and encoded using population codes. Muscle force signals are generated from this representation by downstream systems in the motor cortex and the spinal cord. In this paper, we consider the problem of learning population-coded kinematic sequences in an abstract neural network model of the medial frontal cortex. For concreteness, the sequences are represented as line drawings in a two-dimensional workspace. Learning such sequences presents several challenges because of the internal complexity of the individual sequences and extensive overlap between sequences. We show that, by using a simple module-selection mechanism, our model is capable of learning multiple sequences with complex structure and very high cross-sequence similarity.