# Error Loss Networks

arXiv: https://arxiv.org/abs/2106.03722 · HTML: https://mlsanity.com/paper/2106.03722/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 64 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 15 of 15)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Multi-View Intact Space Learning](https://mlsanity.com/paper/1904.02340/) (2019)
- [Generalized Correntropy for Robust Adaptive Filtering](https://mlsanity.com/paper/1504.02931/) (2015)
- [Restricted Minimum Error Entropy Criterion for Robust Classification](https://mlsanity.com/paper/1909.02707/) (2019)
- [Quantized Minimum Error Entropy Criterion](https://mlsanity.com/paper/1710.04089/) (2017)
- [Robust Learning with Kernel Mean p-Power Error Loss](https://mlsanity.com/paper/1612.07019/) (2016)
- [A Novel Approach to Quantized Matrix Completion Using Huber Loss Measure](https://mlsanity.com/paper/1810.12460/) (2018)
- [Multi-Kernel Correntropy for Robust Learning](https://mlsanity.com/paper/1905.10115/) (2019)
- [Kernel Risk-Sensitive Loss: Definition, Properties and Application to Robust Adaptive Filtering](https://mlsanity.com/paper/1608.00441/) (2016)
- [Robustness analysis of a Maximum Correntropy framework for linear regression](https://mlsanity.com/paper/1703.04829/) (2017)
- [Maximum Correntropy Criterion with Variable Center](https://mlsanity.com/paper/1904.06501/) (2019)
- [A Novel Family of Adaptive Filtering Algorithms Based on The Logarithmic Cost](https://mlsanity.com/paper/1311.6809/) (2013)
- [Maximum Correntropy Unscented Filter](https://mlsanity.com/paper/1608.07526/) (2016)
- [Granger Causality Analysis Based on Quantized Minimum Error Entropy Criterion](https://mlsanity.com/paper/1808.02430/) (2018)

## Built on by (most cited first, 1 of 1)

- [Deep Neural Network-Driven Adaptive Filtering](https://mlsanity.com/paper/2508.04258/) (2025)

## Abstract (arXiv)

A novel model called error loss network (ELN) is proposed to build an error loss function for supervised learning. The ELN is in structure similar to a radial basis function (RBF) neural network, but its input is an error sample and output is a loss corresponding to that error sample. That means the nonlinear input-output mapper of ELN creates an error loss function. The proposed ELN provides a unified model for a large class of error loss functions, which includes some information theoretic learning (ITL) loss functions as special cases. The activation function, weight parameters and network size of the ELN can be predetermined or learned from the error samples. On this basis, we propose a new machine learning paradigm where the learning process is divided into two stages: first, learning a loss function using an ELN; second, using the learned loss function to continue to perform the learning. Experimental results are presented to demonstrate the desirable performance of the new method.