Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 6,731 papers for “Sigmoid function”

Sigmoid function parameters.

Knikou Maria · Figshare · 2015

<p>Summarized sigmoid function parameters calculated from the sigmoid fit applied to the MEP and TEP recruitment curve for each subject and muscle. The first column indicates the maximum size of the action potentials from the recruitment curve (in mV ms), while the second column indicates the R<sup>2</sup> from the sigmoid function. No statistically significant differences were found between the sigmoidal parameters between MEPs and TEPs, across muscles, or between TEPs recorded from the left or right leg (<i>P</i>>0.05). m: slope parameter of the function, S50: stimulus at 50% of the maximal evoked compound action muscle potential. R: right. L: left. TA: tibialis anterior. MG: medialis gastrocnemius. SOL: soleus. PL: peroneus longus.</p>

Cited by 0Open access

Tan-Sigmoid function.

Zhengwei Ma (616975), Wenjia Hou (1817584), Dan Zhang (51283) · Figshare · 2021

Cited by 0Open access

Log-Sigmoid function.

Zhengwei Ma (616975), Wenjia Hou (1817584), Dan Zhang (51283) · Figshare · 2021

Cited by 0Open access

Sigmoid rate function approximation.

Kathrin Pabst (15371194), Evripidis Gkanias (6996494), Barbara Webb (350575) et al. · Figshare · 2024

<p>Green dotted line: rate function of the ideal integrate-and-fire neuron without noise. Blue dashed line: rate function with <i>σ</i> = 8 mV membrane noise, averaged across 1000 simulations. Solid orange line: best fit obtained with a logistic sigmoid. For details, see text.</p> <p>(TIF)</p>

Cited by 0Open access

Activation function (sigmoid and purelin).

M. N. Hudha (19666934), Md. Jahid Hasan (12511378), T. Bairagi (19666937) et al. · Figshare · 2024

<div><p>The objective of the study is to investigate the fluid flow and heat transfer characteristics applying Artificial Neural Networks (ANN) analysis in triangular-shaped cavities for the analysis of magnetohydrodynamics (MHD) mixed convection with varying fluid velocity of water/Al<sub>2</sub>O<sub>3</sub> nanofluid. No study has yet been conducted on this geometric configuration incorporating ANN analysis. Therefore, this study analyzes and predicts the complex interactions among fluid flow, heat transfer, and various influencing factors using ANN analysis. The process of finite element analysis was conducted, and the obtained results have been verified by previous literature. The Levenberg-Marquardt backpropagation technique was selected for ANN. Various values of the Richardson number (0.01 ≤ Ri ≤ 5), Hartmann number (0 ≤ Ha ≤ 100), Reynolds number (50 ≤ Re ≤ 200), and solid volume fraction of the nanofluid (ϕ = 1%, 3% and 4%) have been selected. The ANN model incorporates the Gauss-Newton method and the method of damped least squares, making it suitable for tackling complex problems with a high degree of non-linearity and uncertainty. The findings have been shown through the use of streamlines, isotherm plots, Nusselt numbers, and the estimated Nusselt number obtained by ANN. Increasing the solid volume fraction improves the rate of heat transmission for all situations with varying values of Ri, Re, and Ha. The Nusselt number is greater with larger values of the Ri and Re parameters, but it lessens for higher value of Ha. Furthermore, ANN demonstrates exceptional precision, as evidenced by the Mean Squared Error and R values of 1.05200e-6 and 0.999988, respectively.</p></div>

Cited by 0Open access

Sigmoid function calculating rain probability.

Niccolo Pescetelli (7000043), Patrik Reichert (13189893), Alex Rutherford (464473) · Figshare · 2022

<p>Sigmoid Function Calculating Rain Probability from normalized predictive functions.</p> <p>(PNG)</p>

Cited by 0Open access

Lightness enhancement by sigmoid function

Kh. Abbas, Alias · Journals & Books Hosting (International Knowledge Sharing Platform) · 2017

In this paper we purposed algorithm, to enhancement the contrast and lightening of Color image .it is use to solve the problem of low lightening or non-uniform lightening.The purposed algorithm is called (Lightening Enhancement by Sigmoid Function) " LESF", this algorithm consist of three parts the first Adaptive luminance enhancement second contrast enhancement and third Color restoration.This algorithm compared with other algorithm like (A new nonlinear adaptive enhancement) (NNAE), MSR( multi-scale Retinex ) and Histogram equalization (HE).whenwe compared this algorithm by using entropy, time , Mean Squared Error for hue(Mea-H) and Mean Squared Error for saturation(Mea-S) , we find The result of (LESF) have a good result and better visual Comparing to the other methods

Cited by 0Open access

Sigmoid cognitive contagion function result comparisons.

Nicholas Rabb (11919596), Lenore Cowen (83852), Jan P. de Ruiter (5580161) et al. · Figshare · 2022

<p>The <i>split</i> message set on an ER random graph, <i>N</i> = 250, <i>ρ</i> = 0.05, for agents updating their beliefs based on the sigmoid cognitive contagion function in <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0261811#pone.0261811.e014" target="_blank">Eq (6)</a>. Graphs display percent of agents who believe <i>B</i> with strength <i>b</i> over time. The left graph shows agents parameterized to be “gullible” (<i>α</i> = 1, <i>γ</i> = 7), the middle shows “normal” agents (<i>α</i> = 2, <i>γ</i> = 3), and the right, “stubborn” agents (<i>α</i> = 4, <i>γ</i> = 2).</p>

Cited by 0Open access

Sigmoid transformation function for preprocessing purposes.

Denis Pavliha (440915), Maja M. Mušič (440916), Gregor Serša (4743132) et al. · Figshare · 2015

<p>Presented is an example sigmoid function (B), with approximations of the step function (A: <i>WC = 512, WW = 1</i>) and linear function (C: <i>WC = 512, WW = 2048</i>).</p>

Cited by 0Open access

Benefit function that has sigmoid shape.

Javad Salimi Sartakhti (3605675), Mohammad Hossein Manshaei (3605669), David Basanta (272623) et al. · Figshare · 2017

<p>The function displays a progression with small beginnings that followed by dramatical growth. In this figure, <i>a</i> shows the inflection point of the function and <i>b</i><sub><i>max</i></sub> represents the maximum benefit that an individual can obtain.</p>

Cited by 0Open access

Sigmoid and Tanh activation function diagrams.

Hongwei Bai (1447999), Weiyan Tong (22032834), Zhenkun Geng (22032837) et al. · Figshare · 2025

(a) The sigmoid function, a bounded and differentiable curve that maps real-valued inputs into the range (0, 1). (b) The tanh function, which transforms inputs into the range (−1, 1), offering zero-centered output. Both functions exhibit sigmoid-like shapes and are widely used to introduce non-linearity in neural networks.

Cited by 0Open access

Blind Deblurring Based on Sigmoid Function

Shuhan Sun, Lizhen Duan, Zhiyong Xu et al. · Sensors · 2021

Blind image deblurring, also known as blind image deconvolution, is a long-standing challenge in the field of image processing and low-level vision. To restore a clear version of a severely degraded image, this paper proposes a blind deblurring algorithm based on the sigmoid function, which constructs novel blind deblurring estimators for both the original image and the degradation process by exploring the excellent property of sigmoid function and considering image derivative constraints. Owing to these symmetric and non-linear estimators of low computation complexity, high-quality images can be obtained by the algorithm. The algorithm is also extended to image sequences. The sigmoid function enables the proposed algorithm to achieve state-of-the-art performance in various scenarios, including natural, text, face, and low-illumination images. Furthermore, the method can be extended naturally to non-uniform deblurring. Quantitative and qualitative experimental evaluations indicate that the algorithm can remove the blur effect and improve the image quality of actual and simulated images. Finally, the use of sigmoid function provides a new approach to algorithm performance optimization in the field of image restoration.

Cited by 7Open access

Demand Prediction Model with Sigmoid Function

Yukari Shirota · RePEc: Research Papers in Economics

インフレーションなどにより原材料費が高騰した場合，経営者は価格上昇に転嫁せず，価格据え置きのまま，対応しようとする傾向がある。ハンバーガーなどの飲食物の場合，サイズダウンが方策のひとつとして考え得る。本稿では，そうした局面でどのように数学モデルを用いるかを解説する。顧客満足度の関数としてシグモイド関数を用い，98％に満足度を下げた場合，結果として収入，生産コスト，利潤がどう変動するかをグラフィクスによって示す。また，「価格据え置きのままサイズダウンする際の利潤最大化問題」を定義し，その解法プロセスをモデル化し，解が存在する範囲を可視化で示す。

Cited by 0

CHEBYSHEV POLYNOMIAL APPROXIMATION FOR ACTIVATION SIGMOID FUNCTION

Miroslav Vlček · Neural Network World · 2012

Genetic algorithms (GAs) are stochastic methods that are widely used in search and optimization.The breeding process is the main driving mechanism for GAs that leads the way to find the global optimum.And the initial phase of the breeding process starts with parent selection.The selection utilized in a GA is effective on the convergence speed of the algorithm.A GA can use different selection mechanisms for choosing parents from the population and in many applications the process generally depends on the fitness values of the individuals.Artificial neural networks (ANNs) are used to decide the appropriate parents by the new hybrid algorithm proposed in this study.And the use of neural networks aims to produce better offspring during the GA search.The neural network utilized in this algorithm tries to learn the structural patterns and correlations that enable two parents to produce high-fit offspring.In the breeding process, the first parent is selected based on the fitness value as usual.Then it is the neural network that decides the appropriate mate for the first parent chosen.Hence, the selection mechanism is not solely dependent on the fitness values in this study.The algorithm is tested with seven benchmark functions.It is observed from results of these tests that the new selection method leads genetic algorithm to converge faster.

Cited by 15

Sigmoid Neural Transfer Function Realised by Percolation

Pignon, D., Parmiter, P.J.M., Slack, J.K. et al. · ePrints Soton (University of Southampton) · 1996

An experiment using the phenomenon of percolation has been conducted to demonstrate the implementation of neural functionality (summing and sigmoid transfer). A simple analog approximation to digital percolation is implemented. The device consists of a piece of amorphous silicon with stochastic bit-stream optical inputs, in which a current percolating from one end to the other defines the neuron output, also in the form of a stochastic bit stream. Preliminary experimental results are presented.

Cited by 0Open access

LSTM architecture gates: σ: Sigmoid activation function.

Su Diao (20775570), Yajie Wan (11732476), Danyi Huang (20775573) et al. · Figshare · 2025

tanh: Hyperbolic tangent activation function, Operations: +: Addition, ×: Multiplication, States: X(t): input state, c(t): Current cell state, c(t-1): previous cel state, h(t): Current hidden state, h(t-1): previous hidden state.

Cited by 0Open access