SCG statistics

Tool stats & trends

Looking to identify usage trends or leading experts?


SCG specifications


Unique identifier OMICS_28769
Name SCG
Alternative name Scaled Conjugate Gradient

Publication for Scaled Conjugate Gradient

SCG citations


Discrete Indoor Three Dimensional Localization System Based on Neural Networks Using Visible Light Communication

PMCID: 5948482
PMID: 29601525
DOI: 10.3390/s18041040

[…] s the estimated output and y is the target output used to train the system. (4)J(y^,y)=f(w,b) There are different algorithms to train a neural network, but in this work a Matlab implementation of the Scaled Conjugate Gradient algorithm was used []. During the training process, the weights are adapted in order to minimize the cost function. The training phase can end when the cost function reaches […]


Statistical and Machine Learning forecasting methods: Concerns and ways forward

PLoS One
PMCID: 5870978
PMID: 29584784
DOI: 10.1371/journal.pone.0194889

[…] ractical guidelines suggested by [] aimed at decreasing the computational time needed for constructing the NN model (the number of the hidden layers used is typically of secondary importance []). The Scaled Conjugate Gradient method [] is then used instead of Standard Backpropagation for estimating the optimal weights. The method, which is an alternative of the famous Levenberg-Marquardt algorithm […]


Efficient Cancer Detection Using Multiple Neural Networks

PMCID: 5722487
PMID: 29282435
DOI: 10.1109/JTEHM.2017.2757471

[…] propagation MLPs chosen for this implementation are: 1)Gradient descent with momentum and adaptive learning rate backpropagation .2)Levenberg-Marquardt backpropagation .3)Resilient backpropagation .4)Scaled conjugate gradient backpropagation .5)Conjugate gradient backpropagation with Powell-Beale restarts , .6)Conjugate gradient backpropagation with Fletcher-Reeves updates .Gradient descent with m […]


Classification of Suicide Attempts through a Machine Learning Algorithm Based on Multiple Systemic Psychiatric Scales

PMCID: 5632514
PMID: 29038651
DOI: 10.3389/fpsyt.2017.00192

[…] erial). Two parameters (presence or absence of a suicide attempts) were set as the output. Data were randomly divided into three sets (70% for training, 15% for validation, and 15% for test), and the scaled conjugate gradient method was used for training (, ). Training automatically stopped when validation reached the minimum cross entropy, and the performance of each variable was measured by the […]


Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain

PLoS One
PMCID: 5552261
PMID: 28797034
DOI: 10.1371/journal.pone.0180174

[…] ss of different auditory brain models and encoding schemes under investigation. The MLPs had hidden layer neurons with hyperbolic tangent transfer functions. They were trained until convergence using scaled conjugate gradient descent [] and a cross-entropy loss function. Once the MLPs were trained, their classification outputs were used to fill the confusion matrices used in the information analys […]


Multimodal Bio Inspired Tactile Sensing Module for Surface Characterization †

PMCID: 5490693
PMID: 28545245
DOI: 10.3390/s17061187

[…] idden layer, and seven neurons in the output layer, the latter corresponding to the number of shapes. The activation functions of all neurons are hyperbolic tangents. The network is trained using the scaled conjugate gradient backpropagation algorithm [].The results for the classification of data representing the 5th-wavelet approximation level of each sensor axis are shown in . Each DOF of the MA […]


Looking to check out a full list of citations?

SCG institution(s)
Computer Science Department, University of Aarhus, Aarhus, Denmark

SCG reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review SCG