Kernel-based Translations of Convolutional Networks
arXiv:1903.08131
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.
References in corpus (6)
- Global rates of convergence for nonconvex optimization on manifolds
- Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity
- Convolutional Kernel Networks
- Scattering Networks for Hybrid Representation Learning
- Random Features for Compositional Kernels
- An Alternative to EM for Gaussian Mixture Models: Batch and Stochastic Riemannian Optimization