Learning to generate combinatorial action sequences utilizing the initial sensitivity of deterministic dynamical systems

Authors:
Ryu Nishimoto;Jun Tani
Affiliations:
Brain Science Institute (RIKEN), 2-1 Hirosawa, Wako-shi, Saitama 351-0198, Japan;Brain Science Institute (RIKEN), 2-1 Hirosawa, Wako-shi, Saitama 351-0198, Japan
Venue:
Neural Networks
Year:
2004

Citing 8
Cited 7

A menu of designs for reinforcement learning over time

Neural networks for control
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Higher order recurrent networks and grammatical inference

Advances in neural information processing systems 2
The Induction of Dynamical Recognizers

Machine Learning - Connectionist approaches to language learning
Artificial intelligence (3rd ed.)

Artificial intelligence (3rd ed.)
Exploring the computational capabilities of recurrent neural networks

Exploring the computational capabilities of recurrent neural networks
Multiple paired forward and inverse models for motor control

Neural Networks - Special issue on neural control and robotics: biology and technology
Model-based learning for mobile robot navigation from the dynamicalsystems perspective

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Microslip as a Simulated Artificial Mind

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Learning Multiple Goal-Directed Actions Through Self-Organization of a Dynamic Neural Network Model: A Humanoid Robot Experiment

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
2008 Special Issue: Achieving "organic compositionality" through self-organization: Reviews on brain-inspired robotics experiments

Neural Networks
Acquiring Rules for Rules: Neuro-Dynamical Systems Account for Meta-Cognition

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Learning to imitate stochastic time series in a compositional way by chaos

Neural Networks
Simultaneously emerging Braitenberg codes and compositionality

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Simple and complex behavior learning using behavior hidden Markov model and CobART

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study shows how sensory-action sequences of imitating finite state machines (FSMs) can be learned by utilizing the deterministic dynamics of recurrent neural networks (RNNs). Our experiments indicated that each possible combinatorial sequence can be recalled by specifying its respective initial state value and also that fractal structures appear in this initial state mapping after the learning converges. We also observed that the sequences of mimicking FSMs are encoded utilizing the transient regions rather than the invariant sets of the evolved dynamical systems of the RNNs.