Feedforward Neural Nets

Fine, Terrence L.

doi:10.1002/047134608x.w5106

Cited by 21 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several modeling techniques such as MultiDimensional Scaling (MDS) [5], [6], [7], Sammon Mapping [8], Principal Component Analysis PCA [9] or Feed Forward Neural Networks [11]. In this paper the selected one is Self Organizing Maps [15], two reasons support this decision, the possibility of dimension reduction and the possibility of visualization.…”

Section: A Modelization Of the Segregation Phenomenonmentioning

confidence: 99%

Application of Self Organizing Maps to predict centerline segregation in steel slabs

Diaz

Sancho

Dı́az

et al. 2006

Conference Record of the 2006 IEEE Industry Applications Conference Forty-First IAS Annual Meeting

View full text Add to dashboard Cite

Segregation in steel cast products is an internal defect that can be very harmful when slabs are rolled in heavy plate mills. Several mathematical models of segregation have been developed in previous works; all of them develop some equations to modelize segregation behavior. In this work it is intended to develop a model based on neural networks obtaining a deeper knowledge on this phenomenon. The first trials have been done with a variable selection based on the experience and previous knowledge on segregation. Further studies will include new variable selection and trials with other machine learning techniques such as genetic programming.

show abstract

Section: A Modelization Of the Segregation Phenomenonmentioning

confidence: 99%

Application of Self Organizing Maps to predict centerline segregation in steel slabs

Diaz

Sancho

Dı́az

et al. 2006

Conference Record of the 2006 IEEE Industry Applications Conference Forty-First IAS Annual Meeting

View full text Add to dashboard Cite

show abstract

“…are differentiable to arbitrary order through the chain rule of differentiation, which implies that the error is also differentiable to arbitrary order. Hence, it is possible to make a Taylor's series expansion in w for T [36]. The algorithms for minimizing T are assuming that Taylor's series expansion about a point w 0 that is possibly a local minimum.…”

Section: Theorymentioning

confidence: 99%

Application of artificial neural networks for gradient elution retention modelling in ion chromatography

Bolanča

Cerjan‐Stefanović

Regelja

et al. 2005

J of Separation Science

View full text Add to dashboard Cite

Application of artificial neural networks for gradient elution retention modelling in ion chromatographyGradient elution in ion chromatography (IC) offers several advantages: total analysis time can be significantly reduced, overall resolution of a mixture can be increased, peak shape can be improved (less tailing) and effective sensitivity can be increased (because there is little variation in peak shape). More importantly, it provides the maximum resolution per time unit. The aim of this work was the development of a suitable artificial neural network (ANN) gradient elution retention model that can be used in a variety of applications for method development and retention modelling of inorganic anions in IC. Multilayer perceptron ANNs were used to model the retention behaviour of fluoride, chloride, nitrite, sulphate, bromide, nitrate and phosphate in relation to the starting time of gradient elution and the slope of the linear gradient elution curve. The advantage of the developed model is the application of an optimized twophase training algorithm that enables the researcher to make use of the advantages of first-and second-order training algorithms in one training procedure. This results in better predictive ability, with less time required for the calculations. The number of hidden layer neurons and experimental data points used for the training set were optimized in terms of obtaining a precise and accurate retention model with respect to minimization of unnecessary experimentation and time needed for the calculation procedures. This study shows that developed ANNs are the method of first choice for retention modelling of inorganic anions in IC.

show abstract

“…In details the MLP presented under FNN is one of type of NN. The FNN receive input from one side and generates output to another side (Fine, 1999). In between, it is connected with neurons in different layers in one direction.…”

Section: Introductionmentioning

confidence: 99%

Improved Spider Monkey Optimization Algorithm to train MLP for data classification

Singh¹,

Diallo²,

Xiong³

et al. 2019

3C Tecnología

View full text Add to dashboard Cite

In this paper, the modified Spider Monkey Optimization (SMO) with Multi-Layer Perceptron (MLP) is utilized to solve the classification problem on five different datasets. The MLP is a widely used Neural Network (NN) variant which requires training on specific application to tackle the slow convergence speed and local minima avoidance. The original SMO with MLP experiences the problem of finding the optimal classification result; due to that, the SMO is enhanced by other meta-heuristics algorithm to train the MLP. Based on the concept of no free lunch theorem, there is always a possibility to improve the algorithm. With the same expectation, the performance of the SMO algorithm is improved by using Differential Evolution (DE) and Grey Wolf Optimizer (GWO) algorithm to train the MLP. Likewise, the SMO-DE and SMO-GWO are two different concepts employed to improve efficiency. The results of proposed algorithms are compared with other well-known algorithms such as BBO, PSO, ES, SVM, KNN, and Logistic Regression. The results show that the proposed algorithm performs better than others or they are more competitive.

show abstract

Feedforward Neural Nets

Cited by 21 publications

References 40 publications

Application of Self Organizing Maps to predict centerline segregation in steel slabs

Application of Self Organizing Maps to predict centerline segregation in steel slabs

Application of artificial neural networks for gradient elution retention modelling in ion chromatography

Improved Spider Monkey Optimization Algorithm to train MLP for data classification

Contact Info

Product

Resources

About