A Continuous Convolutional Trainable Filter for Modelling Unstructured Data
This enables CNNs to be applied to complex problems with unstructured domains, representing an incremental advancement in deep learning methods.
The authors tackled the limitation of convolutional neural networks (CNNs) to discrete data by proposing a continuous trainable filter for unstructured data, achieving accuracy comparable to state-of-the-art discrete filters.
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.