Feed-forward network training using optimal input gains

Malalur, Sanjeev S.; Manry, M.T.

doi:10.1109/ijcnn.2009.5178913

Cited by 12 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning in the ONGFE can be triggered in an autonomous way when recognizing particular events. A key capability for on-line automated learning consists of an embedded kernel with fast learning algorithms such as Optimized Conjugate Gradient and Output Weight Optimization-Backpropagation [9]. The ONGFE includes supervised and unsupervised ANN tools, where in the latter case automated clustering of input data is possible which is highly desirable when the nature of the data is not known beforehand.…”

Section: A Optimized Neuro Genetic Fast Estimator (Ongfe)mentioning

confidence: 99%

Self-learning and neural network adaptation by embedded collaborative learning engine (eCLE) — An overview

Galindo

Oonk

2013

The 2013 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

This paper provides an overview of a novel scheme for constructing machine evolutionary behavior within systems. Specifically, evolving learning for the autonomous recognition of both known as well as newly emerging behaviors is provided. The paper is related with several open research problems such as cognition, incremental learning, and selflearning within the context of health monitoring systems (fault diagnosis and prognosis). Also, it is addressed the need for a formal methodology and its implementation for adding new knowledge, thus enabling the automated recognition of new patterns (e.g. behaviors) within systems. A key feature of the resulting embedded Collaborative Learning Engine (eCLE) when generating machine evolutionary behavior consists of operating with an ensemble of learning paradigms, which when instantiated work in a collaborative way. The resulting framework not only compiles the inherent advantages of the involved methods, but also enables synergistic behavior by working in a collaborative fashion.

show abstract

Section: A Optimized Neuro Genetic Fast Estimator (Ongfe)mentioning

confidence: 99%

Self-learning and neural network adaptation by embedded collaborative learning engine (eCLE) — An overview

Galindo

Oonk

2013

The 2013 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…Although first-order full-training methods scale well, they lack affine invariance and are sensitive to the input means and gain factors [28]. To increase convergence per iteration, investigators have looked into second-order training algorithms.…”

Section: Introductionmentioning

confidence: 99%

Multistage Newton’s Approach for Training Radial Basis Function Neural Networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

A systematic four-step batch approach is presented for the second-order training of radial basis function (RBF) neural networks for estimation. First, it is shown that second-order training works best when applied separately to several disjoint parameter subsets. Newton's method is used to find distance measure weights, leading to a kind of embedded feature selection. Next, separate Newton's algorithms are developed for RBF spread parameters, center vectors, and output weights. The final algorithm's training error per iteration and per multiply are compared to those of other algorithms, showing that convergence speed is reasonable. For several widely available datasets, it is shown that tenfold testing errors of the final algorithm are less than those for recursive least squares, the error correction algorithm, the support vector regression training, and Levenberg-Marquardt.

show abstract

“…However second order methods do not scale well and suffer from heavy computational cost. Although first order methods scale better, they are sensitive to input means and gain factor [17].…”

Section: Introductionmentioning

confidence: 99%

An optimal construction and training of second order RBF network for approximation and illumination invariant image segmentation

Cai

Tyagi

Manry

2011

The 2011 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

In this paper, we proposed an hybrid optimal radial-basis function (RBF) neural network for approximation and illumination invariant image segmentation. Unlike other RBF learning algorithms, the proposed paradigm introduces a new way to train RBF models by using optimal learning factors (OLFs) to train the network parameters, i.e. spread parameter, kernel vector and a weighted distance measure (DM) factor to calculate the activation function. An efficient second order Newton's algorithm is proposed for obtaining multiple OLF's (MOLF) for the network parameters. The weights connected to the output layer are trained by a supervised-learning algorithm based on orthogonal least square (OLS). The error obtained is then back-propagated to tune the RBF parameters. By applying RBF network for approximation on some real-life datasets and classification to reduce illumination effects of image segmentation, the results show that the proposed RBF neural network has fast convergence rates combining with low computational time cost, allowing it a good choice for real-life application such as image segmentation.

show abstract

Feed-forward network training using optimal input gains

Cited by 12 publications

References 14 publications

Self-learning and neural network adaptation by embedded collaborative learning engine (eCLE) — An overview

Self-learning and neural network adaptation by embedded collaborative learning engine (eCLE) — An overview

Multistage Newton’s Approach for Training Radial Basis Function Neural Networks

An optimal construction and training of second order RBF network for approximation and illumination invariant image segmentation

Contact Info

Product

Resources

About

Feed-forward network training using optimal input gains

Cited by 12 publications

References 14 publications

Self-learning and neural network adaptation by embedded collaborative learning engine (eCLE) &#x2014; An overview

Self-learning and neural network adaptation by embedded collaborative learning engine (eCLE) &#x2014; An overview

Multistage Newton’s Approach for Training Radial Basis Function Neural Networks

An optimal construction and training of second order RBF network for approximation and illumination invariant image segmentation

Contact Info

Product

Resources

About

Self-learning and neural network adaptation by embedded collaborative learning engine (eCLE) — An overview

Self-learning and neural network adaptation by embedded collaborative learning engine (eCLE) — An overview