Nth Absolute Root Mean Error

Siddhartha Dhar Choudhury; Shashank Pandey

doi:10.35940/ijitee.J9626.119119

Nth Absolute Root Mean Error

Machine Learning 2019-12-16 v2 Machine Learning

Authors: Siddhartha Dhar Choudhury , Shashank Pandey

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

Neural network training process takes long time when the size of training data is huge, without the large set of training values the neural network is unable to learn features. This dilemma between time and size of data is often solved using fast GPUs, but we present a better solution for a subset of those problems. To reduce the time for training a regression model using neural network we introduce a loss function called Nth Absolute Root Mean Error (NARME). It helps to train regression models much faster compared to other existing loss functions. Experiments show that in most use cases NARME reduces the required number of epochs to almost one-tenth of that required by other commonly used loss functions, and also achieves great accuracy in the small amount of time in which it was trained.

Keywords

neural network training neural network neural networks

Cite

@article{arxiv.1810.00421,
  title  = {Nth Absolute Root Mean Error},
  author = {Siddhartha Dhar Choudhury and Shashank Pandey},
  journal= {arXiv preprint arXiv:1810.00421},
  year   = {2019}
}

Comments

12 pages, 13 figures

Related papers

View all related →

Neural and Evolutionary Computing · Computer Science

Artificial Neural Network for Performance Modeling and Optimization of CMOS Analog Circuits

Mriganka Chakraborty

2012-12-13

Neural and Evolutionary Computing · Computer Science

Alternate Loss Functions for Classification and Robust Regression Can Improve the Accuracy of Artificial Neural Networks

Mathew Mithra Noel, Arindam Banerjee, Yug Oswal, Geraldine Bessie Amali D +1