Building recurrent neural networks to implement multiple attractor dynamics using the gradient descent method

Authors:
Jun Namikawa;Jun Tani
Affiliations:
Brain Science Institute, RIKEN, Wako City, Saitama, Japan;Brain Science Institute, RIKEN, Wako City, Saitama, Japan
Venue:
Advances in Artificial Neural Systems
Year:
2009

Citing 10
Cited 0

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Original Contribution: Approximation of dynamical systems by continuous time recurrent neural networks

Neural Networks
Analog computation via neural networks

Theoretical Computer Science
Modeling dynamical systems with recurrent neural networks

Modeling dynamical systems with recurrent neural networks
On the computational power of neural nets

Journal of Computer and System Sciences
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
Learning to generate articulated behavior through the bottom-up and the top-down interaction processes

Neural Networks
Recurrent neural networks with small weights implement definite memory machines

Neural Computation
Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.00

Visualization

Abstract

The present paper proposes a recurrent neural network model and learning algorithm that can acquire the ability to generate desired multiple sequences. The network model is a dynamical system in which the transition function is a contraction mapping, and the learning algorithm is based on the gradient descent method. We show a numerical simulation in which a recurrent neural network obtains a multiple periodic attractor consisting of five Lissajous curves, or a Van der Pol oscillator with twelve different parameters. The present analysis clarifies that the model contains many stable regions as attractors, and multiple time series can be embedded into these regions by using the present learning method.