Importance of input data normalization for the application of neural networks to complex industrial problems

By J. Sola, J. Sevilla. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

Citations in the corpus

Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit (2017, methodology): “This step has been shown to help make the training procedure faster and easier in other applications (Sola & Sevilla 1997).”
The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning (2016, unknown): “This step has been shown to help make the training procedure faster and easier in other applications [42].”
Predicting Cloud Resource Utilization (2016, background): “This process is called normalization and has been shown to greatly improve prediction performance and reduce training time [27].”
A novel hybrid extreme learning machine–grey wolf optimizer (ELM-GWO) model to predict compressive strength of concrete with partial replacements for cement (2020, background): “Therefore, these functions are more sensitive to the input variables which have been normalized prior to training [78].”
Application of artificial neural networks for modeling of biohydrogen production (2013, methodology): “Input and output variables were normalized in the range of ( 1, 1) to avoid any numerical overflow prior to training, as well as reducing the errors and decreasing the training time [27].”
Data Augmentation techniques in time series domain: a survey and taxonomy (2022, background): “neural network (ANN) would be inefficient [115, 116] Although VAEs are algorithms capable of generating synthetic data, as opposed to traditional algorithms that only modify the original data, new neural network (NN) models such as GANs have mitigated their use in the field because by nature they ar”