Results 311 to 320 of about 10,610,136 (340)

Adaptive Friction in Deep Learning: Enhancing Optimizers with Sigmoid and Tanh Function

2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS)
Adaptive optimizers are pivotal in guiding the weight updates of deep neural networks, yet they often face challenges such as poor generalization and oscillation issues.
Hongye Zheng, Bingxing Wang, Minheng Xiao, Honglin Qin, Zhizhong Wu, Lianghao Tan   +5 more
semanticscholar   +1 more source

Sigmoid Function Model for a PFM Power Electronic Converter

IEEE transactions on power electronics, 2020
A power electronic converter is a switching system; the key to modeling it is how to describe the interaction between the discrete switch variables and the continuous state variables in a unified model.
Yimin Lu, X. Huang, Yizheng Huang, Dong Liu   +3 more
semanticscholar   +1 more source

Accuracy controlled iterative method for efficient sigmoid function approximation

Electronics Letters, 2020
The sigmoid activation function plays an essential role in implementing neural networks in hardware. However, due to a high degree of non-linearity, the hardware implementation of the activation function itself is a daunting job.
S. R. Chiluveru, M. Tripathy, B. Mohapatra   +2 more
semanticscholar   +1 more source

A new invertible model of magnetorheological damper based on sigmoid function

Smart materials and structures (Print), 2020
As an intelligent device, the magnetorheological (MR) damper has received extensive attention in many fields. However, in the real-time control system, it is still extremely necessary to develop a simple, accurate and invertible dynamic model of the MR ...
Hongwei Lu, Zhongming Xu, Kaizhan Gao, Zhifei Zhang, Zhi Li, Jujiang Xie   +5 more
semanticscholar   +1 more source

Design of a Rapid Tangent Sigmoid Function Tracking Differentiator

2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), 2020
Aiming at the shortage of differential accuracy of rapid tangent sigmoid tracking differentiator in tracking input signal and the slow convergence of tangent sigmoid tracking differentiator near the equilibrium point and the poor ability to suppress ...
X. Zong, Zhenzhen Chen, Jiangtao Zheng, Xingong Cheng   +3 more
semanticscholar   +1 more source

Why tanh: choosing a sigmoidal function

[Proceedings 1992] IJCNN International Joint Conference on Neural Networks, 2003
As hardware implementations of backpropagation and related training algorithms are anticipated, the choice of a sigmoidal function should be carefully justified. Attention should focus on choosing an activation function in a neural unit that exhibits the best properties for training. The author argues for the use of the hyperbolic tangent.
B.L. Kalman, S.C. Kwasny
openaire   +2 more sources

Efficient Hardware Implementation of DNN-Based Speech Enhancement Algorithm With Precise Sigmoid Activation Function

IEEE Transactions on Circuits and Systems - II - Express Briefs, 2021
This brief presents the hardware implementation of deep neural network-based speech enhancement algorithm (DNN-SEA) with a precise sigmoid activation function. Further, an adaptive step-size-based slope and intercept method (AS-SIM) has been developed to
S. R. Chiluveru, .. Gyanendra, Snehit Chunarkar, M. Tripathy, Brajesh Kumar Kaushik   +4 more
semanticscholar   +1 more source

The new approximation operators with sigmoidal functions

Journal of Applied Mathematics and Computing, 2013
The aim of this paper is to investigate approximation operators with logarithmic sigmoidal function of a class of two neural networks weights and a class of quasi-interpolation operators. Using these operators as approximation tools, the upper bounds of estimate errors are estimated for approximating continuous functions.
Zhengqiu Zhang, Kaiyu Liu, Yanju Chen, Li Zhu   +3 more
openaire   +2 more sources

An Adaptive Algorithm Based On The Sigmoidal Function

2006 Ninth Brazilian Symposium on Neural Networks (SBRN'06), 2006
In this work, we show the development of an adaptive algorithm based on the Ln(cosh \varepsilon) as cost function applied upon the error, called Sigmoidal Algorithm (SA). That function generates a surface which yields fast convergence along with lower misadjustment. It is similar to the family of algorithms proposed by Walach and Widrow [1].
J.C. Principe, Allan Kardec Barros, Raimundo C. S. Freire, Ewaldo Santana   +3 more
openaire   +2 more sources

Approximation by neural networks with sigmoidal functions [PDF]

Acta Mathematica Sinica, English Series, 2013
In this paper, we introduce a type of approximation operators of neural networks with sigmodal functions on compact intervals, and obtain the pointwise and uniform estimates of the approximation. To improve the approximation rate, we further introduce a type of combinations of neural networks.
openaire   +1 more source