Results 31 to 40 of about 220,793 (302)
Approximation by Superpositions of a Sigmoidal Function
Zeitschrift für Analysis und ihre Anwendungen, 2003 We generalize a result of B. Gao and Y. Xu [J. Math. Anal. Appl. 178 (1993) 221–226] concerning the approximation of functions of bounded variation by linear combinations of a fixed sigmoidal function to the class of functions of bounded f-variation. Also, in the case of one variable, a proposition of A. R. Barron [IEEE Trans. Inf. Theory 36 (1993) 930–
LEWICKI G, MARINO, Giuseppe
openaire +4 more sources
Optimal Performance and Application for Seagull Optimization Algorithm Using a Hybrid Strategy
Entropy, 2022 This paper aims to present a novel hybrid algorithm named SPSOA to address problems of low search capability and easy to fall into local optimization of seagull optimization algorithm.
Qingyu Xia +5 more
doaj +1 more source
On The Robustness of a Neural Network [PDF]
, 2017 With the development of neural networks based machine learning and their usage in mission critical applications, voices are rising against the \textit{black box} aspect of neural networks as it becomes crucial to understand their limits and capabilities.
Guerraoui, Rachid +2 more
core +2 more sources
Generalizing the sigmoid function using continuous-valued logic
Fuzzy Sets and Systems, 2022 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
József Dombi, Tamás Jónás
openaire +3 more sources
SinLU: Sinu-Sigmoidal Linear Unit
Mathematics, 2022 Non-linear activation functions are integral parts of deep neural architectures. Given the large and complex dataset of a neural network, its computational complexity and approximation capability can differ significantly based on what activation function
Ashis Paul +4 more
doaj +1 more source
Make the most of your samples : Bayes factor estimators for high-dimensional models of sequence evolution [PDF]
, 2013 Background: Accurate model comparison requires extensive computation times, especially for parameter-rich models of sequence evolution. In the Bayesian framework, model selection is typically performed through the evaluation of a Bayes factor, the ratio ...
Baele, Guy +2 more
core +2 more sources
Kongzhi Yu Xinxi Jishu, 2022 Small wind power generation systems have the characteristics of nonlinear strong coupling and the application requirements of small weight and low cost.
WANG Hongru, ZHANG Zhigang
doaj +1 more source
, 2019 Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in [0,1] through a sigmoid function.
Jang, JoonHo +3 more
core +1 more source
Constructive Approximation by Superposition of Sigmoidal Functions
Analysis in Theory and Applications, 2013 In this paper, a constructive theory is developed for approximating func- tions of one or more variables by superposition of sigmoidal functions. This is done in the uniform norm as well as in the L p norm. Results for the simultaneous approx- imation, with the same order of accuracy, of a function and its derivatives (whenever these exist), are ...
COSTARELLI, DANILO, SPIGLER, Renato
openaire +1 more source
Applications of Modified Sigmoid Functions to a Class of Starlike Functions [PDF]
Journal of Function Spaces, 2020 The main focus of this investigation is the applications of modified sigmoid functions. Due to its various uses in physics, engineering, and computer science, we discuss several geometric properties like necessary and sufficient conditions in the form of convolutions for functions to be in the special classSSG∗earlier introduced by Goel and Kumar and ...
Muhammad Ghaffar Khan +4 more
openaire +3 more sources