Results 291 to 300 of about 220,793 (302)

A class +1 sigmoidal activation functions for FFANNs

Journal of Economic Dynamics and Control, 2003
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Singh, Yogesh, Chandra, Pravin
openaire   +1 more source

Cascade observer synthesis with sigmoid functions

2012 IEEE 11th International Conference on Actual Problems of Electronics Instrument Engineering (APEIE), 2012
The problems of invariant tracking problem for nonlinear under parametrical uncertainty and incomplete miserable are considered. The effective method of the synthesis of the state space observer and external and parametrical disturbances extraction is sliding mode technique.
S. A. Krasnova, N. S. Mysik
openaire   +1 more source

Multivariate neural network operators with sigmoidal activation functions

Neural Networks, 2013
In this paper, we study pointwise and uniform convergence, as well as order of approximation, of a family of linear positive multivariate neural network (NN) operators with sigmoidal activation functions. The order of approximation is studied for functions belonging to suitable Lipschitz classes and using a moment-type approach. The special cases of NN
COSTARELLI, DANILO, SPIGLER, Renato
openaire   +3 more sources

Sigmoid functions used in hysteresis phenomenon modeling

2015 9th International Symposium on Advanced Topics in Electrical Engineering (ATEE), 2015
Hysteresis phenomenon is currently met in magnetic materials characterization. From many years this hysteresis had been modeled with different approaches. The aim of this paper is to present a comparison between few sigmoid functions used more often in other research areas.
Lucian Petrescu, Emil Cazacu, Catalina Petrescu   +2 more
openaire   +1 more source

Fast Backpropagation using Modified Sigmoidal Functions

1994
Backpropagation is the most commonly known algorithm for the adjustment of the weights of an Artificial Neural Network (ANN). It is well known that, in this method the partial derivatives of a criterion function with respect to the weights of a multilayer ANN are determined and the weights of the connections are adjusted pursuing a gradient descent in ...
openaire   +1 more source

Double-exponential sigmoidal functions for neural networks

e & i Elektrotechnik und Informationstechnik, 1997
A computationally efficient sigmoidal activation function is presented, called a double-exponential signal function, and the properties are compared with other signal functions. The sigmoidal function is monotonously increasing, continuous in all derivaties, and its output is 0.5 for zero input.
M. Heiss, S. Kampl
openaire   +1 more source

Polynomial bounds for a class of univalent function involving sigmoid function

2018
Summary: In this work, a new subclass of univalent function was defined using the Sălăgean differential operator involving the modified sigmoid function and the Chebyshev polynomials. The coefficient bounds and the Fekete-Szego functional of this class were obtained using subordination principle.
Fadipe-Joseph, Olubunmi, Kadir, Bilikis, Akinwumi, Sunday, Adeniran, Esther   +3 more
openaire   +2 more sources

Sigmoid orthotopic neobladder; functional results

2000
Long term functional and oncological results of the use of sigmoid colon in neobladder reconstruction after radical ...
NICITA, GIULIO, VILLARI, DONATA, LI MARZI, VINCENZO, Iannelli F, Marzocco M, Della Melina A.   +5 more
openaire   +1 more source

Sigmoid-like Nonlinear Functions

1999
openaire   +1 more source

[Sigmoid function in duodenitis].

Vrachebnoe delo, 1970
openaire   +1 more source