Task Segmentation in a Mobile Robot by mnSOM and Clustering with Spatio-temporal Contiguity

Authors:
M. Aziz Muslim;Masumi Ishikawa;Tetsuo Furukawa
Affiliations:
Dept.of Brain Science and Engineering, Kyushu Institute of Technology, Japan;Dept.of Brain Science and Engineering, Kyushu Institute of Technology, Japan;Dept.of Brain Science and Engineering, Kyushu Institute of Technology, Japan
Venue:
Neural Information Processing
Year:
2008

Citing 7
Cited 0

Gradient-based learning algorithms for recurrent networks and their computational complexity

Backpropagation
Multiple paired forward and inverse models for motor control

Neural Networks - Special issue on neural control and robotics: biology and technology
Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems

Neural Networks - Special issue on organisation of computation in brain-like systems
Self-Organizing Maps

Self-Organizing Maps
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Task segmentation in a mobile robot by mnSOM: a new approach to training expert modules

Neural Computing and Applications
Adaptive mixtures of local experts

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In our previous study, task segmentation by mnSOM implicitly assumes that winner modules corresponding to subsequences in the same class share the same label. This paper proposes to do task segmentation by applying various clustering methods to the resulting mnSOM without using the above assumption. Firstly we use the conventional hierarchical clustering. It assumes that the distances between any pair of modules are provided with precision, but this is not exactly true. Accordingly, this is followed by a clustering based on only the distance between spatially adjacent modules with modification by their temporal contiguity. This clustering with spatio-temporal contiguity provides superior performance to the conventional hierarchical clustering and comparable performance with mnSOM using the implicit assumption.