The Learning Dynamcis of a Universal Approximator

نویسندگان

  • Ansgar Heinrich Ludolf West
  • David Saad
  • Ian T. Nabney
چکیده

The learning properties of a universal approximator, a normalized committee machine with adjustable biases, are studied for on-line back-propagation learning. Within a statistical mechanics framework, numerical studies show that this model has features which do not exist in previously studied two-layer network models without adjustable biases, e.g., attractive suboptimal symmetric phases even for realizable cases and noiseless data.

برای دانلود 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

Universal Approximator Property of the Space of Hyperbolic Tangent Functions

In this paper, first the space of hyperbolic tangent functions is introduced and then the universal approximator property of this space is proved. In fact, by using this space, any nonlinear continuous function can be uniformly approximated with any degree of accuracy. Also, as an application, this space of functions is utilized to design feedback control for a nonlinear dynamical system.

متن کامل

Universal Approximation , With Fuzzy ART and . Fuzzy ARTMAP

A measure of s k c e s s for any learning algorithm is how u s e ful it is in a variety of learning situations. Those learning algorithms that support universal function approximation can theoretically h e applied to a very large and interesting class of learning problems. Many kinds of neural network architectures have already been shown to support universal approximation. In this paper, we wi...

متن کامل

A trainable transparent universal approximator for defuzzification in Mamdani-type neuro-fuzzy controllers

A novel technique of designing application specific defuzzification strategies with neural learning is presented. The proposed neural architecture considered as a universal defuzzification approximator is validated by showing the convergence when approximating several existing defuzzification strategies. The method is successfully tested with fuzzy controlled reverse driving of a model truck. T...

متن کامل

Transfer Reinforcement Learning

The objective of transfer reinforcement learning is to generalize from a set of previous tasks to unseen new tasks. In this work, we focus on the transfer scenario where the dynamics among tasks are the same, but their goals differ. Although general value function (Sutton et al., 2011) has been shown to be useful for knowledge transfer, learning a universal value function can be challenging in ...

متن کامل

A Trainable Transparent Universal Approximator for Defuzzi cation in Mamdani Type Neuro-Fuzzy Controllers

|A novel technique of designing application speci c defuzzi cation strategies with neural learning is presented. The proposed neural architecture considered as a universal defuzzi cation approximator is validated by showing the convergence when approximating several existing defuzzi cation strategies. The method is successfully tested with fuzzy controlled reverse driving of a model truck. The ...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1996