Search results for: steepest descent

Authors: Bib Paruhum Silalahi, Djihad Wungguli, Sugi Guritman

Abstract:

Steepest descent method is a simple gradient method for optimization. This method has a slow convergence in heading to the optimal solution, which occurs because of the zigzag form of the steps. Barzilai and Borwein modified this algorithm so that it performs well for problems with large dimensions. Barzilai and Borwein method results have sparked a lot of research on the method of steepest descent, including alternate minimization gradient method and Yuan method. Inspired by previous works, we modified the step size of the steepest descent method. We then compare the modification results against the Barzilai and Borwein method, alternate minimization gradient method and Yuan method for quadratic function cases in terms of the iterations number and the running time. The average results indicate that the steepest descent method with the new step sizes provide good results for small dimensions and able to compete with the results of Barzilai and Borwein method and the alternate minimization gradient method for large dimensions. The new step sizes have faster convergence compared to the other methods, especially for cases with large dimensions.

Keywords: Convergence, iteration, line search, running time, steepest descent, unconstrained optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3160

Authors: Danupun Visuwan, Pongchanun Luangpaiboon

Abstract:

This paper presents the determination of the proper quality costs parameters which provide the optimum return. The system dynamics simulation was applied. The simulation model was constructed by the real data from a case of the electronic devices manufacturer in Thailand. The Steepest Descent algorithm was employed to optimise. The experimental results show that the company should spend on prevention and appraisal activities for 850 and 10 Baht/day respectively. It provides minimum cumulative total quality cost, which is 258,000 Baht in twelve months. The effect of the step size in the stage of improving the variables to the optimum was also investigated. It can be stated that the smaller step size provided a better result with more experimental runs. However, the different yield in this case is not significant in practice. Therefore, the greater step size is recommended because the region of optima could be reached more easily and rapidly.

Keywords: Quality costs, Steepest Descent Algorithm, StepSize, System Dynamics Simulation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1268

Authors: Shyam S.N. Perera

Abstract:

An optimal control problem for a mathematical model of efficiency of antiviral therapy in hepatitis B virus infections is considered. The aim of the study is to control the new viral production, block the new infection cells and maintain the number of uninfected cells in the given range. The optimal controls represent the efficiency of antiviral therapy in inhibiting viral production and preventing new infections. Defining the cost functional, the optimal control problem is converted into the constrained optimization problem and the first order optimality system is derived. For the numerical simulation, we propose the steepest descent algorithm based on the adjoint variable method. A computer program in MATLAB is developed for the numerical simulations.

Keywords: Virus infection model, Optimal control, Adjoint system, Steepest descent

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1253

Authors: Thiang, Handry Khoswanto, Rendy Pangaldus

Abstract:

Inverse kinematics analysis plays an important role in developing a robot manipulator. But it is not too easy to derive the inverse kinematic equation of a robot manipulator especially robot manipulator which has numerous degree of freedom. This paper describes an application of Artificial Neural Network for modeling the inverse kinematics equation of a robot manipulator. In this case, the robot has three degree of freedoms and the robot was implemented for drilling a printed circuit board. The artificial neural network architecture used for modeling is a multilayer perceptron networks with steepest descent backpropagation training algorithm. The designed artificial neural network has 2 inputs, 2 outputs and varies in number of hidden layer. Experiments were done in variation of number of hidden layer and learning rate. Experimental results show that the best architecture of artificial neural network used for modeling inverse kinematics of is multilayer perceptron with 1 hidden layer and 38 neurons per hidden layer. This network resulted a RMSE value of 0.01474.

Keywords: Artificial neural network, back propagation, inverse kinematics, manipulator, robot.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2288

Authors: R. Uporn, P. Luangpaiboon

Abstract:

This paper presents a comparative study of statistical methods for the multi-response surface optimization of a cryogenic freezing process. Taguchi design and analysis and steepest ascent methods based on the desirability function were conducted to ascertain the influential factors of a cryogenic freezing process and their optimal levels. The more preferable levels of the set point, exhaust fan speed, retention time and flow direction are set at -90oC, 20 Hz, 18 minutes and Counter Current, respectively. The overall desirability level is 0.7044.

Keywords: Cryogenic Freezing Process, Taguchi Design and Analysis, Response Surface Method, Steepest Ascent Method and Desirability Function Approach.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1832

Authors: Shyam S.N. Perera

Abstract:

The optimal control problem for the viscoelastic melt spinning process has not been reported yet in the literature. In this study, an optimal control problem for a mathematical model of a viscoelastic melt spinning process is considered. Maxwell-Oldroyd model is used to describe the rheology of the polymeric material, the fiber is made of. The extrusion velocity of the polymer at the spinneret as well as the velocity and the temperature of the quench air and the fiber length serve as control variables. A constrained optimization problem is derived and the first–order optimality system is set up to obtain the adjoint equations. Numerical solutions are carried out using a steepest descent algorithm. A computer program in MATLAB is developed for simulations.

Keywords: Fiber spinning, Maxwell-Oldroyd, Optimal control, First-order optimality system, Adjoint system

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1888

Authors: Changqiao Wu, Guoqing Ding, Xin Chen

Abstract:

In this paper, ways of modeling dynamic measurement systems are discussed. Specially, for linear system with single-input single-output, it could be modeled with shallow neural network. Then, gradient based optimization algorithms are used for searching the proper coefficients. Besides, method with normal equation and second order gradient descent are proposed to accelerate the modeling process, and ways of better gradient estimation are discussed. It shows that the mathematical essence of the learning objective is maximum likelihood with noises under Gaussian distribution. For conventional gradient descent, the mini-batch learning and gradient with momentum contribute to faster convergence and enhance model ability. Lastly, experimental results proved the effectiveness of second order gradient descent algorithm, and indicated that optimization with normal equation was the most suitable for linear dynamic models.

Keywords: Dynamic system modeling, neural network, normal equation, second order gradient descent.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 781

Authors: Hirofumi Miyajima, Kazuya Kishida, Noritaka Shigei, Hiromi Miyajima

Abstract:

Most of self-tuning fuzzy systems, which are automatically constructed from learning data, are based on the steepest descent method (SDM). However, this approach often requires a large convergence time and gets stuck into a shallow local minimum. One of its solutions is to use fuzzy rule modules with a small number of inputs such as DIRMs (Double-Input Rule Modules) and SIRMs (Single-Input Rule Modules). In this paper, we consider a (generalized) DIRMs model composed of double and single-input rule modules. Further, in order to reduce the redundant modules for the (generalized) DIRMs model, pruning and generative learning algorithms for the model are suggested. In order to show the effectiveness of them, numerical simulations for function approximation, Box-Jenkins and obstacle avoidance problems are performed.

Keywords: Box-Jenkins’s problem, Double-input rule module, Fuzzy inference model, Obstacle avoidance, Single-input rule module.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1957

Authors: Zhifeng Kong

Abstract:

Over-parameterized neural networks have attracted a great deal of attention in recent deep learning theory research, as they challenge the classic perspective of over-fitting when the model has excessive parameters and have gained empirical success in various settings. While a number of theoretical works have been presented to demystify properties of such models, the convergence properties of such models are still far from being thoroughly understood. In this work, we study the convergence properties of training two-hidden-layer partially over-parameterized fully connected networks with the Rectified Linear Unit activation via gradient descent. To our knowledge, this is the first theoretical work to understand convergence properties of deep over-parameterized networks without the equally-wide-hidden-layer assumption and other unrealistic assumptions. We provide a probabilistic lower bound of the widths of hidden layers and proved linear convergence rate of gradient descent. We also conducted experiments on synthetic and real-world datasets to validate our theory.

Keywords: Over-parameterization, Rectified Linear Units (ReLU), convergence, gradient descent, neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 896

Authors: Job H. Domingo, Carolina Bancayrin-Baguio

Abstract:

The Sphere Method is a flexible interior point algorithm for linear programming problems. This was developed mainly by Professor Katta G. Murty. It consists of two steps, the centering step and the descent step. The centering step is the most expensive part of the algorithm. In this centering step we proposed some improvements such as introducing two or more initial feasible solutions as we solve for the more favorable new solution by objective value while working with the rigorous updates of the feasible region along with some ideas integrated in the descent step. An illustration is given confirming the advantage of using the proposed procedure.

Keywords: Interior point, linear programming, sphere method, initial feasible solution, feasible region, centering and descent steps, optimal solution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1803

Authors: Min Sun, Zhenyu Liu

Abstract:

In this paper, a new descent-projection method with a new search direction for monotone structured variational inequalities is proposed. The method is simple, which needs only projections and some function evaluations, so its computational load is very tiny. Under mild conditions on the problem-s data, the method is proved to converges globally. Some preliminary computational results are also reported to illustrate the efficiency of the method.

Keywords: variational inequalities, monotone function, global convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1292

Authors: Varin Chouvatut, Suthep Madarasmi, Mihran Tuceryan

Abstract:

This paper aims to propose a novel, robust, and simple method for obtaining a human 3D face model and camera pose (position and orientation) from a video sequence. Given a video sequence of a face recorded from an off-the-shelf digital camera, feature points used to define facial parts are tracked using the Active- Appearance Model (AAM). Then, the face-s 3D structure and camera pose of each video frame can be simultaneously calculated from the obtained point correspondences. This proposed method is primarily based on the combined approaches of Gradient Descent and Powell-s Multidimensional Minimization. Using this proposed method, temporarily occluded point including the case of self-occlusion does not pose a problem. As long as the point correspondences displayed in the video sequence have enough parallax, these missing points can still be reconstructed.

Keywords: Camera Pose, Face Reconstruction, Gradient Descent, Powell's Multidimensional Minimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1584

Authors: S. Anna Durai, E. Anna Saro

Abstract:

Image Compression using Artificial Neural Networks is a topic where research is being carried out in various directions towards achieving a generalized and economical network. Feedforward Networks using Back propagation Algorithm adopting the method of steepest descent for error minimization is popular and widely adopted and is directly applied to image compression. Various research works are directed towards achieving quick convergence of the network without loss of quality of the restored image. In general the images used for compression are of different types like dark image, high intensity image etc. When these images are compressed using Back-propagation Network, it takes longer time to converge. The reason for this is, the given image may contain a number of distinct gray levels with narrow difference with their neighborhood pixels. If the gray levels of the pixels in an image and their neighbors are mapped in such a way that the difference in the gray levels of the neighbors with the pixel is minimum, then compression ratio as well as the convergence of the network can be improved. To achieve this, a Cumulative distribution function is estimated for the image and it is used to map the image pixels. When the mapped image pixels are used, the Back-propagation Neural Network yields high compression ratio as well as it converges quickly.

Keywords: Back-propagation Neural Network, Cumulative Distribution Function, Correlation, Convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2552

Authors: Young-Seok Choi

Abstract:

We propose two affine projection algorithms (APA) with variable regularization parameter. The proposed algorithms dynamically update the regularization parameter that is fixed in the conventional regularized APA (R-APA) using a gradient descent based approach. By introducing the normalized gradient, the proposed algorithms give birth to an efficient and a robust update scheme for the regularization parameter. Through experiments we demonstrate that the proposed algorithms outperform conventional R-APA in terms of the convergence rate and the misadjustment error.

Keywords: Affine projection, regularization, gradient descent, system identification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1609

Authors: Yakin Hajlaoui, Richard Labib, Jean-Franc¸ois Plante, Michel Gamache

Abstract:

This study presents the Multi-Layer Inverse Distance Weighting Model (ML-IDW), inspired by the mathematical formulation of both multi-layer neural networks (ML-NNs) and Inverse Distance Weighting model (IDW). ML-IDW leverages ML-NNs’ processing capabilities, characterized by compositions of learnable non-linear functions applied to input features, and incorporates IDW’s ability to learn anisotropic spatial dependencies, presenting a promising solution for nonlinear spatial interpolation and learning from complex spatial data. We employ gradient descent and backpropagation to train ML-IDW. The performance of the proposed model is compared against conventional spatial interpolation models such as Kriging and standard IDW on regression and classification tasks using simulated spatial datasets of varying complexity. Our results highlight the efficacy of ML-IDW, particularly in handling complex spatial dataset, exhibiting lower mean square error in regression and higher F1 score in classification.

Keywords: Deep Learning, Multi-Layer Neural Networks, Gradient Descent, Spatial Interpolation, Inverse Distance Weighting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 34

Authors: N. M. Nawi, M. R. Ransing, R. S. Ransing

Abstract:

The conjugate gradient optimization algorithm usually used for nonlinear least squares is presented and is combined with the modified back propagation algorithm yielding a new fast training multilayer perceptron (MLP) algorithm (CGFR/AG). The approaches presented in the paper consist of three steps: (1) Modification on standard back propagation algorithm by introducing gain variation term of the activation function, (2) Calculating the gradient descent on error with respect to the weights and gains values and (3) the determination of the new search direction by exploiting the information calculated by gradient descent in step (2) as well as the previous search direction. The proposed method improved the training efficiency of back propagation algorithm by adaptively modifying the initial search direction. Performance of the proposed method is demonstrated by comparing to the conjugate gradient algorithm from neural network toolbox for the chosen benchmark. The results show that the number of iterations required by the proposed method to converge is less than 20% of what is required by the standard conjugate gradient and neural network toolbox algorithm.

Keywords: Back-propagation, activation function, conjugategradient, search direction, gain variation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2838

Authors: Kevin Spencer G. Anglim, Zhenyu Zhang, Qingbin Gao

Abstract:

Reusable launch vehicles (RLVs) present a more environmentally-friendly approach to accessing space when compared to traditional launch vehicles that are discarded after each flight. This paper studies the recyclable nature of RLVs by presenting a solution method for determining minimum-fuel optimal trajectories using principles from optimal control theory and particle swarm optimization (PSO). This problem is formulated as a minimum-landing error powered descent problem where it is desired to move the RLV from a fixed set of initial conditions to three different sets of terminal conditions. However, unlike other powered descent studies, this paper considers the highly nonlinear effects caused by atmospheric drag, which are often ignored for studies on the Moon or on Mars. Rather than optimizing the controls directly, the throttle control is assumed to be bang-off-bang with a predetermined thrust direction for each phase of flight. The PSO method is verified in a one-dimensional comparison study, and it is then applied to the two-dimensional cases, the results of which are illustrated.

Keywords: Minimum-fuel optimal trajectory, particle swarm optimization, reusable rocket, SpaceX.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2013

Authors: Mehdi Ghayoumi

Abstract:

We have applied new accelerated algorithm for linear discriminate analysis (LDA) in face recognition with support vector machine. The new algorithm has the advantage of optimal selection of the step size. The gradient descent method and new algorithm has been implemented in software and evaluated on the Yale face database B. The eigenfaces of these approaches have been used to training a KNN. Recognition rate with new algorithm is compared with gradient.

Keywords: lda, adaptive, svm, face recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1422

Authors: Helle Hein, Ülo Lepik

Abstract:

A gradient learning method to regulate the trajectories of some nonlinear chaotic systems is proposed. The method is motivated by the gradient descent learning algorithms for neural networks. It is based on two systems: dynamic optimization system and system for finding sensitivities. Numerical results of several examples are presented, which convincingly illustrate the efficiency of the method.

Keywords: Chaos, Dynamical Systems, Learning, Neural Networks

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1366

Authors: Alexander Y. Vaninsky

Abstract:

The objective of this paper is finding the way of economic restructuring - that is, change in the shares of sectoral gross outputs - resulting in the maximum possible increase in the gross domestic product (GDP) combined with decreases in energy consumption and CO₂ emissions. It uses an input-output model for the GDP and factorial models for the energy consumption and CO₂ emissions to determine the projection of the gradient of GDP, and the antigradients of the energy consumption and CO₂ emissions, respectively, on a subspace formed by the structure-related variables. Since the gradient (antigradient) provides a direction of the steepest increase (decrease) of the objective function, and their projections retain this property for the functions' limitation to the subspace, each of the three directional vectors solves a particular problem of optimal structural change. In the next step, a type of factor analysis is applied to find a convex combination of the projected gradient and antigradients having maximal possible positive correlation with each of the three. This convex combination provides the desired direction of the structural change. The national economy of the United States is used as an example of applications.

Keywords: Economic restructuring, Input-Output analysis, Divisia index, Factorial decomposition, E3 models.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1608

Authors: M. Massour El Aoud, M. Franceschi, M. Maher

Abstract:

The approach proposed here is oriented in the direction of fuzzy system for the analysis and the synthesis of intelligent climate controllers, the simulation of the internal climate of the greenhouse is achieved by a linear model whose coefficients are obtained by identification. The use of fuzzy logic controllers for the regulation of climate variables represents a powerful way to minimize the energy cost. Strategies of reduction and optimization are adopted to facilitate the tuning and to reduce the complexity of the controller.

Keywords: Greenhouse, fuzzy logic, optimization, gradient descent.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1947

Authors: Young-Seok Choi

Abstract:

We present a normalized LMS (NLMS) algorithm with robust regularization. Unlike conventional NLMS with the fixed regularization parameter, the proposed approach dynamically updates the regularization parameter. By exploiting a gradient descent direction, we derive a computationally efficient and robust update scheme for the regularization parameter. In simulation, we demonstrate the proposed algorithm outperforms conventional NLMS algorithms in terms of convergence rate and misadjustment error.

Keywords: Regularization, normalized LMS, system identification, robustness.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1876

Authors: Syed Muhammad Aqil Burney, Tahseen Ahmed Jilani, C. Ardil

Abstract:

Financial forecasting is an example of signal processing problems. A number of ways to train/learn the network are available. We have used Levenberg-Marquardt algorithm for error back-propagation for weight adjustment. Pre-processing of data has reduced much of the variation at large scale to small scale, reducing the variation of training data.

Keywords: Gradient descent method, jacobian matrix.Levenberg-Marquardt algorithm, quadratic error surfaces,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2474

Authors: R.Muthuvelayudham, T.Viruthagiri

Abstract:

Response Surface Methodology (RSM) is a powerful and efficient mathematical approach widely applied in the optimization of cultivation process. Cellulase enzyme production by Trichoderma reesei RutC30 using agricultural waste rice straw and banana fiber as carbon source were investigated. In this work, sequential optimization strategy based statistical design was employed to enhance the production of cellulase enzyme through submerged cultivation. A fractional factorial design (26-2) was applied to elucidate the process parameters that significantly affect cellulase production. Temperature, Substrate concentration, Inducer concentration, pH, inoculum age and agitation speed were identified as important process parameters effecting cellulase enzyme synthesis. The concentration of lignocelluloses and lactose (inducer) in the cultivation medium were found to be most significant factors. The steepest ascent method was used to locate the optimal domain and a Central Composite Design (CCD) was used to estimate the quadratic response surface from which the factor levels for maximum production of cellulase were determined.

Keywords: Banana fiber, Cellulase, Optimization, Rice straw

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2400

Authors: Mohamed Boulouird, Moha M'Rabet Hassani

Abstract:

In this paper, many techniques for blind identification of moving average (MA) process are presented. These methods utilize third- and fourth-order cumulants of the noisy observations of the system output. The system is driven by an independent and identically distributed (i.i.d) non-Gaussian sequence that is not observed. Two nonlinear optimization algorithms, namely the Gradient Descent and the Gauss-Newton algorithms are exposed. An algorithm based on the joint-diagonalization of the fourth-order cumulant matrices (FOSI) is also considered, as well as an improved version of the classical C(q, 0, k) algorithm based on the choice of the Best 1-D Slice of fourth-order cumulants. To illustrate the effectiveness of our methods, various simulation examples are presented.

Keywords: Cumulants, Identification, MA models, Parameter estimation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1408

Authors: B. Selma, S. Chouraqui

Abstract:

Nonlinear system identification is becoming an important tool which can be used to improve control performance. This paper describes the application of adaptive neuro-fuzzy inference system (ANFIS) model for controlling a car. The vehicle must follow a predefined path by supervised learning. Backpropagation gradient descent method was performed to train the ANFIS system. The performance of the ANFIS model was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed ANFIS model has potential in controlling the non linear system.

Keywords: Adaptive neuro-fuzzy inference system (ANFIS), Fuzzy logic, neural network, nonlinear system, control

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1785

Authors: Min Sun, Jing Liu

Abstract:

In this article, a new inexact alternating direction method(ADM) is proposed for solving a class of variational inequality problems. At each iteration, the new method firstly solves the resulting subproblems of ADM approximately to generate an temporal point ˜xk, and then the multiplier yk is updated to get the new iterate yk+1. In order to get xk+1, we adopt a new descent direction which is simple compared with the existing prediction-correction type ADMs. For the inexact ADM, the resulting proximal subproblem has closedform solution when the proximal parameter and inexact term are chosen appropriately. We show the efficiency of the inexact ADM numerically by some preliminary numerical experiments.

Keywords: variational inequality problems, alternating direction method, global convergence

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1498

Authors: B. Q. Huang, Tarik Rashid, M-T. Kechadi

Abstract:

this paper presents a multi-context recurrent network for time series analysis. While simple recurrent network (SRN) are very popular among recurrent neural networks, they still have some shortcomings in terms of learning speed and accuracy that need to be addressed. To solve these problems, we proposed a multi-context recurrent network (MCRN) with three different learning algorithms. The performance of this network is evaluated on some real-world application such as handwriting recognition and energy load forecasting. We study the performance of this network and we compared it to a very well established SRN. The experimental results showed that MCRN is very efficient and very well suited to time series analysis and its applications.

Keywords: Gradient descent method, recurrent neural network, learning algorithms, time series, BP

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3043

Authors: Syed Muhammad Aqil Burney, Tahseen Ahmed Jilani, C. Ardil

Abstract:

Minimization methods for training feed-forward networks with Backpropagation are compared. Feedforward network training is a special case of functional minimization, where no explicit model of the data is assumed. Therefore due to the high dimensionality of the data, linearization of the training problem through use of orthogonal basis functions is not desirable. The focus is functional minimization on any basis. A number of methods based on local gradient and Hessian matrices are discussed. Modifications of many methods of first and second order training methods are considered. Using share rates data, experimentally it is proved that Conjugate gradient and Quasi Newton?s methods outperformed the Gradient Descent methods. In case of the Levenberg-Marquardt algorithm is of special interest in financial forecasting.

Keywords: Backpropagation algorithm, conjugacy condition, line search, matrix perturbation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3643

Authors: Vigen Arakelian

Abstract:

This paper deals with the study of devices for displacement of the mould base of blow-molding machines. The displacement of the mould in the studied case is carried out by a linear actuator, which ensures the descent of the mould base and by extension springs, which return the letter in the initial position. The aim of this paper is to study the inverse dynamics of the device for displacement of the mould base of blow-molding machines and to determine its optimum parameters for higher rate of production. In the other words, it is necessary to solve the inverse dynamic problem to find the equation of motion linking applied forces with displacements. This makes it possible to determine the stiffness coefficient of the spring to turn the mold base back to the initial position for a given time. The obtained results are illustrated by a numerical example. It is shown that applying a spring with stiffness returns the mould base of the blow molding machine into the initial position in 0.1 sec.

Keywords: Design, blow-molding machines, dynamics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 690