Neural Networks and Their Applications

Clothiaux, Eugene E.; Bachmann, Charles M.

doi:10.1007/978-94-011-1122-5_2

Cited by 9 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural nets have the ability to generalize relationships from a small subset of data and to handle noisy inputs or missing input parameters (Hewitson and Crane, 1994). The mathematical structure of various neural net forms are detailed in Clothiaux and Bachmann (1994) but a simplified discussion of neural net structures should suffice here, as described in Hewitson and Crane (1994). A neural net is a group of interconnected processing nodes connected by weighted links (Figure 7).…”

Section: Neural Network Analysismentioning

confidence: 99%

Synoptic controls on upper Colorado River basin snowfall

McGinnis

2000

Int. J. Climatol.

View full text Add to dashboard Cite

Section: Neural Network Analysismentioning

confidence: 99%

Synoptic controls on upper Colorado River basin snowfall

McGinnis

2000

Int. J. Climatol.

View full text Add to dashboard Cite

“…If errors are outside the predetermined cutoff limits and tbe maximum number of learning cycles has not been reached, then the total normalized error for all training pixels is used by tbe Generalized Delta Rule to reweight each connection during back-propagation (CLOTHIAUX and BACHMANN, 1994). Tben the next learning cycle is begun.…”

Section: Trainingmentioning

confidence: 99%

Artificial Neural Network Classification of Sand in all Visible Submarine and Subaerial Regions of a Digital Image

Conger¹,

Fletcher²,

Barbee³

2005

Journal of Coastal Research

View full text Add to dashboard Cite

Factors controlling the distribution of shelf sand as a resource, a component of reef ecosystems, and a dynamic substrate are poorly understood. An initial step in understanding sand accumulation in each of these roles is to identify its areal extent and change through time. Digitized aerial photographs and digital images provide common, inexpensive data sets that are generally underutilized for the purpose of marine sub.strate classification. Here we use only two bands, blue and green (470 and 550 nm), to demonstrate the utility of simple aerial photography in classifying marine substrate. Although these two are acquired from a hyperspectral data set, they represent blue and green in an RGB image such as commonly available in digitized aerial photographs. We add as a third band the second eigenchannel of a principal components analysis of these bands. Using an artificial neural network classification model, we identify submarine and subaerial sandy .substrate in a digital image of a detached reef island in the Red Sea, Gezirat Siyul, Egypt. With careful selection of training and test groups, using small percentages of the total classified image, we create an efficient and accurate classification model. The model, trained to identify two classes, "sand" and "other than sand," produces a clas.sified image that pro\'ides sand locations and approximate areal coverage. Confusion matrices for both training and testing groups have user's accuracies in the 90 percentiies, indicating accurate pixel classification.

show abstract

“…The common and conventional approach [11][12][13][14][15][16][17][18] for the design of output layer nodes is as follows: The output layer contains r output nodes corresponding to the r classes. For an input sample of the i-th class (1 ≤ i ≤ r), the ideal output is 1 for the i-th output node, and 0 for all the other output nodes.…”

Section: Introductionmentioning

confidence: 99%

Binary Output Layer of Feedforward Neural Networks for Solving Multi-Class Classification Problems

Yang

Zhang

2019

IEEE Access

View full text Add to dashboard Cite

Considered in this short note is the design of output layer nodes of feedforward neural networks for solving multi-class classification problems with r (r ≥ 3) classes of samples. The common and conventional setting of output layer, called "one-to-one approach" in this paper, is as follows: The output layer contains r output nodes corresponding to the r classes. And for an input sample of the i-th class (1 ≤ i ≤ r), the ideal output is 1 for the i-th output node, and 0 for all the other output nodes. We propose in this paper a new "binary approach": Suppose 2 q−1 < r ≤ 2 q with q ≥ 2, then we let the output layer contain q output nodes, and let the ideal outputs for the r classes be designed in a binary manner. Numerical experiments carried out in this paper show that our binary approach does equally good job as, but uses less output nodes than, the traditional one-to-one approach.

show abstract

Neural Networks and Their Applications

Cited by 9 publications

References 40 publications

Synoptic controls on upper Colorado River basin snowfall

Synoptic controls on upper Colorado River basin snowfall

Artificial Neural Network Classification of Sand in all Visible Submarine and Subaerial Regions of a Digital Image

Binary Output Layer of Feedforward Neural Networks for Solving Multi-Class Classification Problems

Contact Info

Product

Resources

About