Open AccessThe effect of Z-Score standardization (normalization) on binary input due the speed of learning in back-propagation neural network
Author(s) -
Mohammed Z. Al-Faiz,
Ali Abdulhafidh Ibrahim,
Sarmad M. Hadi
Publication year - 2019
Publication title -
iraqi journal of information and communication technology/iraqi journal of information and communication technology
Language(s) - English
Resource type - Journals
eISSN - 2789-7362
pISSN - 2222-758X
DOI - 10.31987/ijict.1.3.41
Subject(s) - standardization , artificial neural network , normalization (sociology) , computer science , artificial intelligence , backpropagation , binary number , data mining , machine learning , database normalization , time delay neural network , set (abstract data type) , data set , binary classification , pattern recognition (psychology) , mathematics , arithmetic , sociology , anthropology , programming language , operating system , support vector machine
The speed of learning in neural network environment is considered as the most effective parameter spatially in large data sets. This paper tries to minimize the time required for the neural network to fully understand and learn about the data by standardize input data. The paper showed that the Z-Score standardization of input data significantly decreased the number of epoochs required for the network to learn. This paper also proved that the binary dataset is a serious limitation for the convergence of neural network, so the standardization is a must in such case where the 0’s inputs simply neglect the connections in the neural network. The data set used in this paper are features extracted from gel electrophoresis images and that open the door for using artificial intelligence in such areas.