.png){kind=icon}
返回
Do Neural Network Weights Account for Classes Centers?
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2022.3153134.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The exploitation of deep neural networks (DNNs) as descriptors in feature learning challenges enjoys apparent popularity over the past few years. The above tendency focuses on the development of effective loss functions that ensure both high feature discrimination among different classes, as well as low geodesic distance between the feature vectors of a given class. The vast majority of the contemporary works rely their formulation on an empirical assumption about the feature space of a network's last hidden layer, claiming that the weight vector of a class accounts for its geometrical center in the studied space. This article at hand follows a theoretical approach and indicates that the aforementioned hypothesis is not exclusively met. This fact raises stability issues regarding the training procedure of a DNN, as shown in our experimental study. Consequently, a specific symmetry is proposed and studied both analytically and empirically that satisfies the above assumption, addressing the established convergence issues. More specifically, the aforementioned symmetry suggests that all weight vectors are unit, coplanar, and their vector summation equals zero. Such a layout is proven to ensure a more stable learning curve compared against the corresponding ones succeeded by popular models in the field of feature learning.
Keyword:
Training
Representation learning
Neural networks
Layout
Task analysis
Feature extraction
Deep learning
Deep neural networks (DNNs)
discriminative feature learning
geometric algebra
symmetrical layer
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
分享收藏分享收藏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