Abstract
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.
Highlights
Back-propagation neural network has proved itself as a very useful method in artificial intelligent field, due to the speed and accuracy, but in large datasets the story is different, back propagation takes a lot of time to learn about the data especially in low hamming-distance input data
The standard score is a very useful statistic because it (a) allows the programmer to calculate the probability of a score occurring within our normal distribution and (b) enables comparing two scores that are from different normal distributions
Several attempts have been done in terms of standardization of input data, this paper introduces using Z-score with binary data-set which can be considered new due to preparing the data to be fed into neural network
Summary
Back-propagation neural network has proved itself as a very useful method in artificial intelligent field, due to the speed and accuracy, but in large datasets the story is different, back propagation takes a lot of time to learn about the data especially in low hamming-distance input data. The output itself plays a role in the speed of learning especially due to the nature of operation in this paper which is input-output mapping where each input must be mapped to a unique and independent output, where this number denotes to a unique identifier for each input.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
