Phase space learning in an autonomous dynamical neural network

نویسندگان

  • Hiroshi Inazawa
  • Garrison W. Cottrell
چکیده

In this paper, we present an improved version of the online phase-space learning algorithm of Tsung and Cottrell (1995), called ARTISTE (Autonomous Real-TIme Selection of Training Examples). The new version’s advantages derive from an online adaptive learning rate that depends on the error. We demonstrate the algorithm’s efficacy on two problems: learning a pair of sine waves offset by 901 and the van der Pol oscillator. The online version of the algorithm allows the system to learn as it behaves. We show that the adaptive learning rate technique gives us excellent results in the learning of the above two tasks. Published by Elsevier B.V.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Calibration of an Inertial Accelerometer using Trained Neural Network by Levenberg-Marquardt Algorithm for Vehicle Navigation

The designing of advanced driver assistance systems and autonomous vehicles needs measurement of dynamical variations of vehicle, such as acceleration, velocity and yaw rate. Designed adaptive controllers to control lateral and longitudinal vehicle dynamics are based on the measured variables. Inertial MEMS-based sensors have some benefits including low price and low consumption that make them ...

متن کامل

An Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network

RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...

متن کامل

A Dynamical Systems Approach for a Learnable Autonomous Robot

This paper discusses how a robot can learn goal-directed navigation tasks using local sensory inputs. The emphasis is that such learning tasks could be formulated as an embedding problem of dynamical systems: desired trajectories in a task space should be embedded into an adequate sensory-based internal state space so that an unique mapping from the internal state space to the motor command cou...

متن کامل

Verification of an Evolutionary-based Wavelet Neural Network Model for Nonlinear Function Approximation

Nonlinear function approximation is one of the most important tasks in system analysis and identification. Several models have been presented to achieve an accurate approximation on nonlinear mathematics functions. However, the majority of the models are specific to certain problems and systems. In this paper, an evolutionary-based wavelet neural network model is proposed for structure definiti...

متن کامل

The Process of Learning Dynamical Systems in Neural Networks and Riddled Basins

Learning chaotic dynamical systems in neural networks is analyzed as a te~nporal evolution process in a non-autonomous discrete dynamical system driven by a chaotic teacher signal, defined on the space of connection weights. It is proved to be impossible to derive the condition for the learning converging to the optimal state in general. The proof is based on the stability analysis of the linea...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Neurocomputing

دوره 69  شماره 

صفحات  -

تاریخ انتشار 2006