Title :
Performance measures for neural nets using Johnson distributions
Author :
Torrez, William C. ; Durham, Jayson T. ; Trueblood, Richard D.
Author_Institution :
ORINCON Corp., San Diego, CA, USA
Abstract :
A probability distribution for multilayer perceptron artificial neural net outputs is derived, assuming a sigmoidal activation function. This distribution is known to be a member of the Johnson system of distributions. Using this distribution, theoretical receiver operating characteristic curves can be developed to obtain recognition differential values for corresponding values of the probability of false alarm. The application of these techniques for the detection of broadband signals is presented
Keywords :
feedforward neural nets; probability; receivers; signal detection; Johnson distributions; artificial neural net outputs; broadband signals; false alarm; multilayer perceptron; probability; probability distribution; receiver operating characteristic curves; recognition differential values; sigmoidal activation function; Artificial neural networks; Character recognition; Information processing; Logistics; Neural networks; Noise shaping; Probability distribution; Random variables; Shape; Signal processing;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298609
