Sigmoidal Function

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 6411 Experts worldwide ranked by ideXlab platform

Pravin Chandra - One of the best experts on this subject based on the ideXlab platform.

  • bi modal derivative adaptive activation Function Sigmoidal feedforward artificial neural networks
    Applied Soft Computing, 2017
    Co-Authors: Akash Mishra, Pravin Chandra, Udayan Ghose, Sartaj Singh Sodhi
    Abstract:

    Abstract In this work an adaptive mechanism for choosing the activation Function is proposed and described. Four bi-modal derivative Sigmoidal adaptive activation Function is used as the activation Function at the hidden layer of a single hidden layer Sigmoidal feedforward artificial neural networks. These four bi-modal derivative activation Functions are grouped as asymmetric and anti-symmetric activation Functions (in groups of two each). For the purpose of comparison, the logistic Function (an asymmetric Function) and the Function obtained by subtracting 0.5 from it (an anti-symmetric) Function is also used as activation Function for the hidden layer nodes’. The resilient backpropagation algorithm with improved weight-tracking (iRprop+) is used to adapt the parameter of the activation Functions and also the weights and/or biases of the Sigmoidal feedforward artificial neural networks. The learning tasks used to demonstrate the efficacy and efficiency of the proposed mechanism are 10 Function approximation tasks and four real benchmark problems taken from the UCI machine learning repository. The obtained results demonstrate that both for asymmetric as well as anti-symmetric activation usage, the proposed/used adaptive activation Functions are demonstratively as good as if not better than the Sigmoidal Function without any adaptive parameter when used as activation Function of the hidden layer nodes.

  • a non Sigmoidal activation Function for feedforward artificial neural networks
    International Joint Conference on Neural Network, 2015
    Co-Authors: Pravin Chandra, Udayan Ghose, Apoorvi Sood
    Abstract:

    For a single hidden layer feedforward artificial neural network to possess the universal approximation property, it is sufficient that the hidden layer nodes activation Functions are continuous non-polynomial Function. It is not required that the activation Function be a Sigmoidal Function. In this paper a simple continuous, bounded, non-constant, differentiable, non-sigmoid and non-polynomial Function is proposed, for usage as the activation Function at hidden layer nodes. The proposed activation Function does require the computation of an exponential Function, and thus is computationally less intensive as compared to either the log-sigmoid or the hyperbolic tangent Function. On a set of 10 Function approximation tasks we demonstrate the efficiency and efficacy of the usage of the proposed activation Functions. The results obtained allow us to assert that, at least on the 10 Function approximation tasks, the results demonstrate that in equal epochs of training, the networks using the proposed activation Function reach deeper minima of the error Functional and also generalize better in most of the cases, and statistically are as good as if not better than networks using the logistic Function as the activation Function at the hidden nodes.

  • a constructive algorithm with adaptive Sigmoidal Function for designing single hidden layer feedforward neural network
    Advanced Materials Research, 2011
    Co-Authors: Sudhir Kumar Sharma, Pravin Chandra
    Abstract:

    In this paper we propose a constructive algorithm with adaptive Sigmoidal Function for designing single hidden layer feedforward neural network (CAASF). The proposed algorithm emphasizes on architectural adaptation and Functional adaptation during training. This algorithm is a constructive approach to building single hidden layer neural networks dynamically. The activation Functions used at non-linear hidden nodes are belonging to the well-defined Sigmoidal class and adapted during training. The algorithm determines not only optimum number of hidden nodes, as also optimum Sigmoidal Function for the non-linear nodes. One simple variant derived from CAASF is where the Sigmoidal Function used at the hidden nodes is fixed. Both the variants are compared to each other on five regression Functions. Simulation results reveal that adaptive Sigmoidal Function presents several advantages over traditional fixed sigmoid Function, resulting in increased flexibility, smoother learning, better convergence and better generalization performance.

  • Cascading Neural Networks Using Adaptive Sigmoidal Function
    Trans Tech Publications Ltd., 2011
    Co-Authors: Sudhir Kumar Sharma, Pravin Chandra
    Abstract:

    This paper presents cascading neural networks using adaptive Sigmoidal Function (CNNASF). The proposed algorithm emphasizes on architectural adaptation and Functional adaptation during training. This algorithm is a constructive approach to building cascading architecture dynamically. The activation Functions used at the hidden layers’ node are belonging to the well-defined Sigmoidal class and adapted during training. The algorithm determines not only optimum number of hidden layers’ node, as also optimum Sigmoidal Function for them. One simple variant derived from CNNASF is where the sigmoid Function used at the hidden layers’ node is fixed. Both the variants are compared to each other on five regression Functions. Simulation results reveal that adaptive Sigmoidal Function presents several advantages over traditional fixed sigmoid Function, resulting in increased flexibility, smoother learning, better convergence and better generalization performance.

  • an adaptive Sigmoidal activation Function cascading neural networks
    Soft Computing, 2011
    Co-Authors: Sudhir Kumar Sharma, Pravin Chandra
    Abstract:

    In this paper, we propose an adaptive Sigmoidal activation Function cascading neural networks. The proposed algorithm emphasizes architectural adaptation and Functional adaptation during training. This algorithm is a constructive approach to building cascading architecture dynamically. To achieve Functional adaptation, an adaptive Sigmoidal activation Function is proposed for the hidden layers’ node. The algorithm determines not only optimum number of hidden layers’ nodes, as also optimum Sigmoidal Function for them. Four variants of the proposed algorithm are developed and discussed on the basis of activation Function used. All the variants are empirically evaluated on five regression Functions in terms of learning accuracy and generalization capability. Simulation results reveal that adaptive Sigmoidal activation Function presents several advantages over traditional fixed sigmoid Function, resulting in increased flexibility, smoother learning, better learning accuracy and better generalization performance.

Ajit D. Kelkar - One of the best experts on this subject based on the ideXlab platform.

  • stiffness degradation model for biaxial braided composites under fatigue loading
    Composites Part B-engineering, 2008
    Co-Authors: Jitendra S Tate, Ajit D. Kelkar
    Abstract:

    Abstract Biaxial braided composites are gaining popularity, in particular for the small business jets, where FAA requires take off weights of 5670 kgf (12,500 lb). In the present research carbon/epoxy biaxial braided composites were manufactured using low cost vacuum assisted resin transfer molding (VARTM). Extensive tension–tension fatigue tests were performed on biaxial braided carbon/epoxy composites for various braid angles. Experimental data clearly indicated that S – N diagram could be represented by Sigmoidal Function. This paper specifically addresses stiffness degradation of braided composites with braid angle of 25°. In addition to Sigmoidal Function, it was observed that the three stages of stiffness degradation curve can be represented by Bradley Function. Sigmoidal Function in conjunction with Bradley Function is explored to predict the fatigue life and the residual fatigue modulus.

  • effect of braid angle on fatigue performance of biaxial braided composites
    International Journal of Fatigue, 2006
    Co-Authors: Jitendra S Tate, Ajit D. Kelkar, John D Whitcomb
    Abstract:

    Abstract Biaxial braided fabric is gaining popularity in primary structural application in small business jets because of its natural ability to conform to complex shapes. This research addresses the effect of braid angle on in-plane mechanical properties and fatigue performance. The carbon/epoxy braided composites were fabricated using low cost vacuum assisted resin transfer molding (VARTM) with different braid angles (25°, 30° and 45°). The static tests were performed to evaluate tensile strength, modulus, and Poisson’s ratio. It is observed that as braid angle increases the tensile strength, modulus, and Poisson’s ratio decreases significantly. The load controlled tension-tension fatigue tests (R = 0.1) were conducted at 10 Hz frequency with constant amplitude. The endurance limit was defined as the fatigue load that results in a fatigue life of one million cycles. The endurance limit for 25° and 30° braided composites was 40% of UTS whereas for 45° braided composites it was 50% of UTS. However, braid angle did not significantly affect the failure mechanism under fatigue loading. It was very crucial to control the braid angle within a test specimen, as tensile strength is significantly affected by braid angle variation. The special form of biaxial braided fabric termed slit sleeves assures the constant braid angle while handling and processing. It was observed that, a Sigmoidal Function could be used effectively to represent the fatigue life behavior. Braided composites exhibited substantially different fatigue failure behavior as compared to conventional angle-ply laminated composites. The major difference being that the failure is sudden. There were hardly any noticeable matrix cracks or delaminations in the first 90% of the fatigue life at all fatigue load levels. There is rapid damage accumulation in the last 10% of the fatigue life.

Jitendra S Tate - One of the best experts on this subject based on the ideXlab platform.

  • stiffness degradation model for biaxial braided composites under fatigue loading
    Composites Part B-engineering, 2008
    Co-Authors: Jitendra S Tate, Ajit D. Kelkar
    Abstract:

    Abstract Biaxial braided composites are gaining popularity, in particular for the small business jets, where FAA requires take off weights of 5670 kgf (12,500 lb). In the present research carbon/epoxy biaxial braided composites were manufactured using low cost vacuum assisted resin transfer molding (VARTM). Extensive tension–tension fatigue tests were performed on biaxial braided carbon/epoxy composites for various braid angles. Experimental data clearly indicated that S – N diagram could be represented by Sigmoidal Function. This paper specifically addresses stiffness degradation of braided composites with braid angle of 25°. In addition to Sigmoidal Function, it was observed that the three stages of stiffness degradation curve can be represented by Bradley Function. Sigmoidal Function in conjunction with Bradley Function is explored to predict the fatigue life and the residual fatigue modulus.

  • effect of braid angle on fatigue performance of biaxial braided composites
    International Journal of Fatigue, 2006
    Co-Authors: Jitendra S Tate, Ajit D. Kelkar, John D Whitcomb
    Abstract:

    Abstract Biaxial braided fabric is gaining popularity in primary structural application in small business jets because of its natural ability to conform to complex shapes. This research addresses the effect of braid angle on in-plane mechanical properties and fatigue performance. The carbon/epoxy braided composites were fabricated using low cost vacuum assisted resin transfer molding (VARTM) with different braid angles (25°, 30° and 45°). The static tests were performed to evaluate tensile strength, modulus, and Poisson’s ratio. It is observed that as braid angle increases the tensile strength, modulus, and Poisson’s ratio decreases significantly. The load controlled tension-tension fatigue tests (R = 0.1) were conducted at 10 Hz frequency with constant amplitude. The endurance limit was defined as the fatigue load that results in a fatigue life of one million cycles. The endurance limit for 25° and 30° braided composites was 40% of UTS whereas for 45° braided composites it was 50% of UTS. However, braid angle did not significantly affect the failure mechanism under fatigue loading. It was very crucial to control the braid angle within a test specimen, as tensile strength is significantly affected by braid angle variation. The special form of biaxial braided fabric termed slit sleeves assures the constant braid angle while handling and processing. It was observed that, a Sigmoidal Function could be used effectively to represent the fatigue life behavior. Braided composites exhibited substantially different fatigue failure behavior as compared to conventional angle-ply laminated composites. The major difference being that the failure is sudden. There were hardly any noticeable matrix cracks or delaminations in the first 90% of the fatigue life at all fatigue load levels. There is rapid damage accumulation in the last 10% of the fatigue life.

U B Desai - One of the best experts on this subject based on the ideXlab platform.

  • image restoration using a multilayer perceptron with a multilevel Sigmoidal Function
    IEEE Transactions on Signal Processing, 1993
    Co-Authors: Krishnamoorthy Sivakumar, U B Desai
    Abstract:

    The problem of restoring a blurred and noisy image having many gray levels, without any knowledge of the blurring Function and the statistics of the additive noise, is considered. A multilevel Sigmoidal Function is used as the node nonlinearlity. The same number of nodes as in the case of a binary image is sufficient for an image with multiple gray levels. Restoration is achieved by exploiting the generalization capabilities of the multilayer perceptron network. For realistic images, training time becomes a major burden. To overcome this, a segmentation scheme is suggested. Simulation results are provided. >

  • image restoration using a multilayer perceptron with a multilevel Sigmoidal Function
    International Symposium on Circuits and Systems, 1992
    Co-Authors: Krishnamoorthy Sivakumar, U B Desai
    Abstract:

    The problem of restoring a blurred and noisy image having many gray levels, without any knowledge of the blurring Function and the statistics of the additive noise is considered. A multilevel Sigmoidal Function is used as the node linearity. Restoration is achieved by exploiting the generalization capabilities of the multilayer perceptron network. To overcome the burden of training time a segmentation scheme is suggested. Simulation results are also provided. >

Petri, Denise F. S. - One of the best experts on this subject based on the ideXlab platform.

  • Poly(ethylene glycol) decorated poly(methylmethacrylate) nanoparticles for protein adsorption
    ELSEVIER SCIENCE BV, 2011
    Co-Authors: Bonfa Alfredo, Saito, Rafael S. N., Franca, Rafael F. O., Fonseca, Benedito A. L., Petri, Denise F. S.
    Abstract:

    Poly(ethylene glycol) decorated poly( methyl methacrylate) particles were synthesized by means of emulsion polymerization using poly(ethylene glycol) sorbitan monolaurate (Tween-20) as surfactant. PMMA/PEG particles presented mean diameter (195 +/- 15) nm, indicating narrow size distribution. The adsorption behavior of bovine serum albumin (BSA) and concanavalin A (ConA) onto PMMA/PEG particles was investigated by means of spectrophotometry. Adsorption isotherms obtained for BSA onto PMMA/PEG particles fitted well Sigmoidal Function, which is typical for multilayer adsorption. Con A adsorbed irreversibly onto PMMA/PEG particles. The efficiency of ConA covered particles to induce dengue virus quick agglutination was evaluated. (C) 2010 Elsevier B.V. All rights reserved.CNPqFAPES

  • Poly(ethylene glycol) decorated poly(methylmethacrylate) nanoparticles for protein adsorption
    ELSEVIER SCIENCE BV, 2011
    Co-Authors: Bonfa Alfredo, Saito, Rafael S. N., Franca, Rafael F. O., Fonseca, Benedito A. L., Petri, Denise F. S.
    Abstract:

    Poly(ethylene glycol) decorated poly( methyl methacrylate) particles were synthesized by means of emulsion polymerization using poly(ethylene glycol) sorbitan monolaurate (Tween-20) as surfactant. PMMA/PEG particles presented mean diameter (195 +/- 15) nm, indicating narrow size distribution. The adsorption behavior of bovine serum albumin (BSA) and concanavalin A (ConA) onto PMMA/PEG particles was investigated by means of spectrophotometry. Adsorption isotherms obtained for BSA onto PMMA/PEG particles fitted well Sigmoidal Function, which is typical for multilayer adsorption. Con A adsorbed irreversibly onto PMMA/PEG particles. The efficiency of ConA covered particles to induce dengue virus quick agglutination was evaluated. (C) 2010 Elsevier B.V. All rights reserved

Related terms

Sigmoidal Function - 15 days free trial to Access Experts & Abstracts