Finding hidden-feature depending laws inside a data set and classifying it using Neural Network

01/25/2021
by   Thilo Moshagen, et al.
0

The logcosh loss function for neural networks has been developed to combine the advantage of the absolute error loss function of not overweighting outliers with the advantage of the mean square error of continuous derivative near the mean, which makes the last phase of learning easier. It is clear, and one experiences it soon, that in the case of clustered data, an artificial neural network with logcosh loss learns the bigger cluster rather than the mean of the two. Even more so, the ANN, when used for regression of a set-valued function, will learn a value close to one of the choices, in other words, one branch of the set-valued function, while a mean-square-error NN will learn the value in between. This work suggests a method that uses artificial neural networks with logcosh loss to find the branches of set-valued mappings in parameter-outcome sample sets and classifies the samples according to those branches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/14/2020

Classification based on invisible features and thereby finding the effect of tuberculosis vaccine on COVID-19

In the case of clustered data, an artificial neural network with logcosh...
research
07/15/2019

Concentration of the matrix-valued minimum mean-square error in optimal Bayesian inference

We consider Bayesian inference of signals with vector-valued entries. Ex...
research
09/23/2015

Well Tops Guided Prediction of Reservoir Properties using Modular Neural Network Concept A Case Study from Western Onshore, India

This paper proposes a complete framework consisting pre-processing, mode...
research
11/26/2018

Frequency Principle in Deep Learning with General Loss Functions and Its Potential Application

Previous studies have shown that deep neural networks (DNNs) with common...
research
11/30/2021

A Scheme of Channel Prediction Based on Artificial Neural Network

Accurate channel modeling is the foundation of communication system desi...
research
12/06/2020

Guitar Effects Recognition and Parameter Estimation with Convolutional Neural Networks

Despite the popularity of guitar effects, there is very little existing ...
research
10/06/2020

A Novel Neural Network Training Framework with Data Assimilation

In recent years, the prosperity of deep learning has revolutionized the ...

Please sign up or login with your details

Forgot password? Click here to reset