.png){kind=icon}
返回
Distance profile layer for binary classification and density estimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2024.127436.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The research on methods trying to explain solutions based on Neural Networks (NN) is a vivid target of Machine Learning works in recent years. Such a need arose due to the black-box nature of neural models and their tendency to provide a high certainty for incorrect decisions regarding events outside the area covered by the training set. In this work, we present a novel layer building a Distance Profile of recognized samples, aiming to substitute one -hot encoding of labels. The presented approach shows promising results in classification and unsupervised distribution density estimation and maintains a consistent representation for both recognition tasks. This approach manages certainty quantification for objects outside of the scope represented by available data and could potentially contribute to the Open Set Recognition and Out of Distribution Detection research fields.
Keyword:
Classification
Distribution density estimation
Neural networks
Open set recognition
Out of distribution detection
Explainable AI
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
分享收藏A review of uncertainty quantification in deep learning: Techniques, applications and challenges深度学习中的不确定性量化: 技术、应用与挑战.png)
INFORMATION FUSION
OAAI
INFORMATION FUSIONIF15.5
OAAI分享收藏Neural Network-Based Uncertainty Quantification: A Survey of Methodologies and Applications基于神经网络的不确定性量化: 方法与应用综述IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks避免过拟合: 卷积神经网络正则化方法综述
OAAI
OAAI分享收藏分享收藏
查看更多内容