A scaled conjugate gradient algorithm for fast supervised learning M. Møller Computer Science Neural Networks 1993 3,768 PDF View 2 excerpts, references methods Controlling industrial processes through supervised, feedforward neural networks Alice E. Smith, C. Dagli Computer Science 1991 26 View 1 excerpt NEURBT, a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. NEURBT is based on Møller's scaled conjugate gradient algorithm which is a variation of the traditional conjugate gradient method, better suited for the non-quadratic nature of neural networks. A supervised learning algorithm (Scaled Conjugate Gradient, SCG) with superlinear convergence rate is introduced. The algorithm is based upon a class of optimization techniques well known in numerical analysis as the Conjugate Gradient Methods. SCG uses second order information from the neural network but requires only O(N) memory usage, where N is the number of weights in the network. In this article, we use neural networks based on three different learning algorithms, i.e., Levenberg-Marquardt, Scaled Conjugate Gradient and Bayesian Regularization for stock market prediction based on tick data as well as 15-min data of an Indian company and their results compared. Abstract: A new second order algorithm based on Scaled Conjugate Gradient for training recurrent and locally recurrent neural networks is proposed. The algorithm is able to extract second order information performing two times the corresponding first order method. A multi-layer neural network with multiple hidden layers was trained as an autoencoder using steepest descent, scaled conjugate gradient and alopex algorithms and results indicate that while pretraining is important for obtaining good results, the pretraining approach used by Hinton et al. obtains lower RMSE than other methods. A multi-layer neural network with multiple hidden layers was there are many types of learning algorithm in artificial neural network that are available in the matlab such as levenberg-marquardt (lm), bayesian regularization (br), bfgs quasi-newton (bfg), resilient backprogagation (rp), scaled conjugate gradient (scg), conjugate gradient with powell/beale restarts (cgb), … The wind energy generation depends upon the nature of direction of wind and varying wind speed. This paper presents the comparison of different wind speed forecasting algorithms i.e. Regression Method and Neural Network (different neural network algorithms- 1. Levenberg-Marquardt 2. Bayesian Regularization 3. Scaled Conjugate Gradient.). Matlab tool is used to find the result of these methods In this paper we discuss NEURBT, a Fortran 77 program for computing neural networks for classification using batch learning. NEURBT is based on Møller's scaled conjugate gradient algorithm [7] which is a variation of the traditional conjugate gradient method [5], better suited for the nonquadratic nature of neural networks. 3.1 Artificial Neural Networks and MLP ANNs can be defined in many ways. At one extreme, the answer could be that neural networks are simply a class of mathematical algorithms, since a network can be regarded essentially as a graphic notation for a large class of algorithms. Such algorithms produce solutions to a number of specific problems. This paper pro