.png){kind=icon}
返回
Levenberg-Marquardt multi-classification using hinge loss function
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2021.07.010.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Incorporating higher-order optimization functions, such as Levenberg-Marquardt (LM) have revealed better generalizable solutions for deep learning problems. However, these higher-order optimization functions suffer from very large processing time and training complexity especially as training datasets become large, such as in multi-view classification problems, where finding global optima is a very costly problem. To solve this issue, we develop a solution for LM-enabled classification with, to the best of knowledge first-time implementation of hinge loss, for multiview classification. Hinge loss allows the neural network to converge faster and perform better than other loss functions such as logistic or square loss rates. We prove our method by experimenting with various multiclass classification challenges of varying complexity and training data size. The empirical results show the training time and accuracy rates achieved, highlighting how our method outperforms in all cases, especially when training time is limited. Our paper presents important results in the relationship between optimization and loss functions and how these can impact deep learning problems. (C) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Neural networks
Levenberg-Marquardt
Hinge loss
Loss functions
Classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Aflatoxin excretion in children with kwashiorkor or marasmic kwashiorkor — a clinical investigation
PREAI
分享收藏Ethylene glycol based silicon nitride nanofluids: An experimental study on their thermophysical, electrical and optical properties乙二醇基氮化硅纳米流体的热物理、电学和光学性质的实验研究
PREAI
分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容