Multi-directional continuous association with input-driven neural dynamics

Authors:
Christian Emmerich;René Felix Reinhart;Jochen Jakob Steil
Affiliations:
Research Institute for Cognition and Robotics-CoR-Lab, Bielefeld University, Universitätsstr. 25, 33615 Bielefeld, Germany;Research Institute for Cognition and Robotics-CoR-Lab, Bielefeld University, Universitätsstr. 25, 33615 Bielefeld, Germany;Research Institute for Cognition and Robotics-CoR-Lab, Bielefeld University, Universitätsstr. 25, 33615 Bielefeld, Germany
Venue:
Neurocomputing
Year:
2013

Citing 9
Cited 0

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics
Neutral Learning of Constrained Nonlinear Transformations

Computer
2007 Special Issue: Optimization and applications of echo state networks with leaky- integrator neurons

Neural Networks
An empirical evaluation of deep architectures on problems with many factors of variation

Proceedings of the 24th international conference on Machine learning
Generative Modeling of Autonomous Robots and their Environments using Reservoir Computing

Neural Processing Letters
Stable Output Feedback in Reservoir Computing Using Ridge Regression

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Recurrent Neural Associative Learning of Forward and Inverse Kinematics for Movement Generation of the Redundant PA-10 Robot

LAB-RS '08 Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems
Correlation Matrix Memories

IEEE Transactions on Computers
Regularization and stability in reservoir networks with output feedback

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

We present an input-driven dynamical system approach to continuous association. Previous formulations of associative reservoir computing networks and associative extreme learning machines are unified and generalized to multiple modalities. Association in these networks proceeds by externally driving parts of the network. Through continuous variation of driving inputs, a continuous association of output patterns is achieved. Robust association in this scheme requires to cope with potential error amplification of feedback dynamics and to handle differently sized input and output modalities such that the outcome of association is controlled by the driving inputs. We propose a dendritic neuron model in combination with a regularization technique to address both issues. The presented method allows for tuning contributions from each modality to the hidden representation by prescribed factors while the regularization of network weights mitigates the problem of error amplification. The scalability of the approach to high-dimensional applications is demonstrated in image and audio processing scenarios.