Kernel-based Translations of Convolutional Networks
From MaRDI portal
Publication:6315896
arXiv1903.08131MaRDI QIDQ6315896
Author name not available (Why is that?)
Publication date: 19 March 2019
Abstract: Convolutional Neural Networks, as most artificial neural networks, are commonly viewed as methods different in essence from kernel-based methods. We provide a systematic translation of Convolutional Neural Networks (ConvNets) into their kernel-based counterparts, Convolutional Kernel Networks (CKNs), and demonstrate that this perception is unfounded both formally and empirically. We show that, given a Convolutional Neural Network, we can design a corresponding Convolutional Kernel Network, easily trainable using a new stochastic gradient algorithm based on an accurate gradient computation, that performs on par with its Convolutional Neural Network counterpart. We present experimental results supporting our claims on landmark ConvNet architectures comparing each ConvNet to its CKN counterpart over several parameter settings.
Has companion code repository: https://github.com/cjones6/yesweckn
This page was built for publication: Kernel-based Translations of Convolutional Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6315896)
