.png){kind=icon}
返回
A continuous convolutional trainable filter for modelling unstructured data
.png){kind=icon}
OA
AI
DOI：10.1007/s00466-023-02291-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional Neural Network (CNN) is one of the most important architectures in deep learning. The fundamental building block of a CNN is a trainable filter, represented as a discrete grid, used to perform convolution on discrete input data. In this work, we propose a continuous version of a trainable convolutional filter able to work also with unstructured data. This new framework allows exploring CNNs beyond discrete domains, enlarging the usage of this important learning technique for many more complex problems. Our experiments show that the continuous filter can achieve a level of accuracy comparable to the state-of-the-art discrete filter, and that it can be used in current deep learning architectures as a building block to solve problems with unstructured domains as well.
Keyword:
Convolutional neural network
Continuous filter
Deep learning
Unstructured data
期刊
IF:
3.8
论文数:
3.2K
被引数:
9.0K
机构
引用论文
Pt182–190andOs180–188isotopes in the phenomenological interacting boson modelPt182–190和Os180–188同位素在唯象的相互作用玻色子模型中
PREAI
分享收藏Real-time and offline techniques for identifying obstructive sleep apnea patients用于识别阻塞性睡眠呼吸暂停患者的实时和离线技术
PREAI
分享收藏Supramolecular Approaches for Taming the Chemo- and Regiochemistry of C60 Addition Reactions驯服C60加成反应的化学和区域化学的超分子方法
OAAI
OAAI分享收藏Patient Reported Outcomes (PROs) in Clinical Trials: Is ‘In-Trial’ Guidance Lacking? A Systematic Review.png)
PLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容