Related Experiment Videos
On the closure of the set of functions that can be realized by a given multilayer perceptron
M Gori1, F Scarselli, A C Tsoi
1Dipartimento d'Ingegneria dell'Informazione, Università di Siena, Italy.
Abstract:
Given a multilayer perceptron (MLP) with a fixed architecture, there are functions that can be approximated up to any degree of accuracy, without having to increase the number of the hidden nodes. Those functions belong to the closure F of the set F of the maps realizable by the MLP. In this paper, we give a list of maps with this property. In particular, it is proven that 1) rational functions belongs to F for networks with inverse tangent activation function and 2) products of polynomials and exponentials belongs to F for networks with sigmoid activation function. Moreover, for a restricted class of MLP's, we prove that the list is complete and give an analytic definition of F.
Related Concept Videos
Multi-input and Multi-variable systems
In the absence of...
Open and closed-loop control systems
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal and...
Neural Regulation
Limits of Multivariable Functions
Network Function of a Circuit
Neural Circuits
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...