Incremental acquisition of multiple nonlinear forward models based on differentiation process of schema model

Authors:
Tadahiro Taniguchi;Tetsuo Sawaragi
Affiliations:
Graduate School of Informatics, Kyoto University, Japan;Graduate School of Engineering, Kyoto University, Japan
Venue:
Neural Networks
Year:
2008

Citing 13
Cited 0

Matrix computations (3rd ed.)

Matrix computations (3rd ed.)
Locally Weighted Learning

Artificial Intelligence Review - Special issue on lazy learning
Multiple paired forward and inverse models for motor control

Neural Networks - Special issue on neural control and robotics: biology and technology
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
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
Using Humanoid Robots to Study Human Behavior

IEEE Intelligent Systems
Multiple model-based reinforcement learning

Neural Computation
Composite adaptive control with locally weighted statistical learning

Neural Networks
MOSAIC Model for Sensorimotor Learning and Control

Neural Computation
On-line EM Algorithm for the Normalized Gaussian Network

Neural Computation
Constructive Incremental Learning from Only Local Information

Neural Computation
Adaptive mixtures of local experts

Neural Computation
Fast learning in networks of locally-tuned processing units

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce the schema model as an alternative computational model representing multiple internal models. The human central nervous system is believed to obtain multiple forward-inverse models. The schema model enables agents to obtain multiple nonlinear forward models incrementally. This model is based on hypothesis testing theory whereas most modular learning methods are based on a Bayesian framework. As a specific example, we describe a schema model with a normalized Gaussian network (NGSM). Simulation revealed that NGSM has two advantages over MOSAIC's learning method: NGSM can obtain multiple models incrementally and does not depend on the initial parameters of the forward models.