Minimum mean square estimation and neural networks

Manry, M.T.; Apollo, S.J.; Yu, Qiang

doi:10.1016/0925-2312(95)00101-8

Cited by 11 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a loosely defined sense, ANN classification is a process of searching optimal solution of weight vector that minimizes the sum of squared errors between network and desired output responses. Manry et al showed that a neural network can approximate the minimum mean square estimator arbitrarily well, provided that it is of adequate size and is well-trained [10]. In this study, by using trial and error, two hidden layers were used, and four nods were adopted.…”

mentioning

confidence: 99%

Reservoir Drought Prediction Using Support Vector Machines

Chiang

Tsai

2011

AMM

View full text Add to dashboard Cite

In Taiwan, even though the average annual rainfall is up to 2500 mm, water shortage during the dry season happens sometimes. Especially in recent years, water shortage has seriously affected the agriculture, industry, commerce, and even the essential daily water use. Under the threat of climate change in the future, efficient use of water resources becomes even more challenging. For a comparative study, support vector machine (SVM) and other three models (artificial neural networks, maximum likelihood classifier, Bayesian classifier) were established to predict reservoir drought status in next 10-90 days in Tsengwen Reservoir. (The ten-days time interval was applied in this study as it is the conventional time unit for reservoir operation.) Four features (which are easily obtainable in most reservoir offices), including reservoir storage capacity, inflows, critical limit of operation rule curves, and the number of ten-days in a year, were used as input data to predict drought. The records of years from 1975 to 1999 were selected as training data, and those of years from 2000 to 2010 were selected as testing data. The empirical results showed that SVM outperforms the other three approaches for drought prediction. Unsurprisingly the longer the prediction time period is, the lower the prediction accuracy is. However, the accuracy of predicting next 50 days is about 85% both in training and testing data set by SVM. As a result, we believe that the SVM model has high potential for predicting reservoir drought due to its high prediction accuracy and simple input data.

show abstract

mentioning

confidence: 99%

Reservoir Drought Prediction Using Support Vector Machines

Chiang

Tsai

2011

AMM

View full text Add to dashboard Cite

show abstract

“…It has the universal approximation property [3]. With proper training, the MLP approximates the Bayes classifier [4] or the minimum mean square error (mmse) estimator [5]. The MLP has found use in many applications including character recognition [6] [7], power load forecasting [8], prognostics [9], well logging [10], and data mining [11].…”

Section: Introductionmentioning

confidence: 99%

Optimal output gain algorithm for feed-forward network training

Aswathappa

Manry

Rawat

2011

The 2011 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

show abstract

“…The relatively short evaluation time make it a better choice than many other classification and approximation methods such as support vector machines (SVM) [35]. The universal approximation [9] property of the MLP along with its ability to mimic Bayes discriminant [10], optimal L2 norm estimates [8] and maximum a-posteriori(MAP) [11] estimates…”

mentioning

confidence: 99%

Analysis and improvement of multiple optimal learning factors for feed-forward networks

Jesudhas

Manry

Rawat

et al. 2011

The 2011 International Joint Conference on Neural Networks

Self Cite

View full text Add to dashboard Cite

are analyzed. The use of optimal diagonal transformation matrices on the net function vector is proved to be equivalent to training the MLP using multiple optimal learning factors (MOLF). A method for linearly compressing large ill-conditioned MOLF Hessian matrices into smaller wellconditioned ones is developed. This compression approach is shown to be equivalent to using several hidden units per learning factor. The technique is extended to large networks. In simulations, the proposed algorithm performs almost as well as the Levenberg Marquardt (LM) algorithm with the computational complexity of a first order training algorithm.

show abstract

Minimum mean square estimation and neural networks

Cited by 11 publications

References 29 publications

Reservoir Drought Prediction Using Support Vector Machines

Reservoir Drought Prediction Using Support Vector Machines

Optimal output gain algorithm for feed-forward network training

Analysis and improvement of multiple optimal learning factors for feed-forward networks

Contact Info

Product

Resources

About