Title :
Extreme learning machine for function approximation - interval problem of input weights and biases
Author_Institution :
Dept. of Electr. Eng., Czestochowa Univ. of Technol., Czestochowa, Poland
Abstract :
In this article the approximation capability of the extreme learning machine is studied. Specifically the impact of the range from which the input weights and biases are randomly generated on the fitted curve complexity is analyzed. The guidance for how to generate the input weights and biases to get good performance in approximation of the functions of one variable is provided.
Keywords :
computational complexity; curve fitting; function approximation; learning (artificial intelligence); mathematics computing; extreme learning machine; fitted curve complexity; function approximation; interval problem; Complexity theory; Fitting; Function approximation; Neurons; Noise; Training; extreme learning machine; feedforward neural networks; function approximation;
Conference_Titel :
Cybernetics (CYBCONF), 2015 IEEE 2nd International Conference on
Conference_Location :
Gdynia
Print_ISBN :
978-1-4799-8320-9
DOI :
10.1109/CYBConf.2015.7175907
