Computational Neural Networks for Geophysical Data by M.M. Poulton

By M.M. Poulton

This publication was once basically written for an viewers that has heard approximately neural networks or has had a few event with the algorithms, yet want to achieve a deeper knowing of the basic fabric. for people that have already got a great seize of ways to create a neural community program, this paintings delivers a variety of examples of nuances in community layout, information set layout, checking out procedure, and blunder analysis.Computational, instead of synthetic, modifiers are used for neural networks during this publication to make a contrast among networks which are applied in and people who are carried out in software program. The time period synthetic neural community covers any implementation that's inorganic and is the main normal time period. Computational neural networks are just carried out in software program yet symbolize the majority of applications.While this e-book can't offer a blue print for each available geophysics software, it does define a easy strategy that has been used effectively.

Show description

Read Online or Download Computational Neural Networks for Geophysical Data Processing (Handbook of Geophysical Exploration: Seismic Exploration) PDF

Best mining books

Classification, Clustering, and Data Mining Applications: Proceedings of the Meeting of the International Federation of Classification Societies ... Data Analysis, and Knowledge Organization)

This quantity describes new equipment with distinctive emphasis on category and cluster research. those equipment are utilized to difficulties in info retrieval, phylogeny, clinical prognosis, microarrays, and different lively examine components.

Petroleum Geoscience: From Sedimentary Environments to Rock Physics

This accomplished textbook provides an outline of petroleum geoscience for geologists energetic within the petroleum undefined, whereas additionally supplying an invaluable advisor for college students drawn to environmental geology, engineering geology and different points of sedimentary geology. during this moment variation, new chapters were extra and others improved, overlaying geophysical tools typically and electromagnetic exploration equipment specifically, in addition to reservoir modeling and construction, unconventional assets and sensible petroleum exploration.

Additional resources for Computational Neural Networks for Geophysical Data Processing (Handbook of Geophysical Exploration: Seismic Exploration)

Example text

BACK-PROPAGATION 14 ,. 12 class=00100 10 / 8 ! 1. A scatterplot of data points and their corresponding classification. The data can be used as input to a neural network for supervised training. The class boundaries indicate that the problem is not linearly separable and therefore appropriate for a non-linear network such as back-propagation. Input Pattern 9 ,..... 2. A sample training file. The input pattern is represented by x- and y-coordinates of data points. The corresponding output pattern is a classification of the datum location.

1 shows a scatter plot where the points have been classified into one of three possible classes. The class boundaries are drawn as straight lines to help separate the points on the plot. The classes have been assigned a binary code that can be used for network training. 1 with two input values representing x- and y-coordinate values and five output values representing five possible classes for the input data points. The output coding is referred to as "l-of-n" coding since only one bit is active for any pattern.

CHAPTER 3. 3. A feed-forward multi-layer Perceptron architecture typically used with a backpropagation learning algorithm. 2. 2) t=l where Sumj represents the weighted sum for a PE in the hidden layer. The connection weight vector ~ represents all the connections weights between a PE in the hidden layer and all of the input PEs. The input vector Y contains one element tbr each value in the training set. 0. 6. In subsequent equations the bias connection weights will be assumed to be part of the weight vector Y and will not be shown as a separate term.

Download PDF sample

Rated 4.18 of 5 – based on 31 votes

Categories: Mining