International Journal of Machine Learning and Cybernetics, Volume (11), No (4), Year (2020-4) , Pages (751-761)

Title : ( Combination of loss functions for deep text classification )

Authors: hamideh hajiabadi , Diego Molla Aliod , Reza Monsefi , Hadi Sadoghi Yazdi ,

Access to full-text not allowed by authors

Citation: BibTeX | EndNote

Abstract

Ensemble methods have shown to improve the results of statistical classifiers by combining multiple single learners into a strong one. In this paper, we explore the use of ensemble methods at the level of the objective function of a deep neural network. We propose a novel objective function that is a linear combination of single losses and integrate the proposed objective function into a deep neural network. By doing so, the weights associated with the linear combination of losses are learned by back propagation during the training stage. We study the impact of such an ensemble loss function on the state-of-the-art convolutional neural networks for text classification. We show the effectiveness of our approach through comprehensive experiments on text classification. The experimental results demonstrate a significant improvement compared with the conventional state-of-the-art methods in the literature.

Keywords

, Loss Function · Convolutional neural network (CNN) · Ensemble method · Multi, class classifer
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@article{paperid:1082479,
author = {Hajiabadi, Hamideh and Diego Molla Aliod and Monsefi, Reza and Sadoghi Yazdi, Hadi},
title = {Combination of loss functions for deep text classification},
journal = {International Journal of Machine Learning and Cybernetics},
year = {2020},
volume = {11},
number = {4},
month = {April},
issn = {1868-8071},
pages = {751--761},
numpages = {10},
keywords = {Loss Function · Convolutional neural network (CNN) · Ensemble method · Multi-class classifer},
}

[Download]

%0 Journal Article
%T Combination of loss functions for deep text classification
%A Hajiabadi, Hamideh
%A Diego Molla Aliod
%A Monsefi, Reza
%A Sadoghi Yazdi, Hadi
%J International Journal of Machine Learning and Cybernetics
%@ 1868-8071
%D 2020

[Download]