Data Normalization to Accelerate Training for Linear Neural Net to Predict Tropical Cyclone Tracks

Jian Jin, Ming Li and Long Jin

Mathematical Problems in Engineering, 2015, vol. 2015, 1-8

Abstract:

When pure linear neural network (PLNN) is used to predict tropical cyclone tracks (TCTs) in South China Sea, whether the data is normalized or not greatly affects the training process. In this paper, min.-max. method and normal distribution method, instead of standard normal distribution, are applied to TCT data before modeling. We propose the experimental schemes in which, with min.-max. method, the min.-max. value pair of each variable is mapped to (−1, 1) and (0, 1); with normal distribution method, each variable’s mean and standard deviation pair is set to (0, 1) and (100, 1). We present the following results: (1) data scaled to the similar intervals have similar effects, no matter the use of min.-max. or normal distribution method; (2) mapping data to around 0 gains much faster training speed than mapping them to the intervals far away from 0 or using unnormalized raw data, although all of them can approach the same lower level after certain steps from their training error curves. This could be useful to decide data normalization method when PLNN is used individually.

Date: 2015
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://downloads.hindawi.com/journals/MPE/2015/931629.pdf (application/pdf)
http://downloads.hindawi.com/journals/MPE/2015/931629.xml (text/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnlmpe:931629

DOI: 10.1155/2015/931629

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().