all AI news
QCNN: Quadrature Convolutional Neural Network with Application to Unstructured Data Compression. (arXiv:2211.05151v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
We present a new convolution layer for deep learning architectures which we
call QuadConv -- an approximation to continuous convolution via quadrature. Our
operator is developed explicitly for use on unstructured data, and accomplishes
this by learning a continuous kernel that can be sampled at arbitrary
locations. In the setting of neural compression, we show that a QuadConv-based
autoencoder, resulting in a Quadrature Convolutional Neural Network (QCNN), can
match the performance of standard discrete convolutions on structured uniform
data, as …
application arxiv compression convolutional neural network data data compression network neural network unstructured data