We develop a unified model, known as MgNet, that simultaneously recovers some convolutional neural networks (CNN) for image classification and multigrid (MG) methods for solving discretized partial differential equations (PDEs). This model is based on close connections that we have observed and uncovered between the CNN and MG methodologies. For example, pooling operation and feature extraction in CNN correspond directly to restriction operation and iterative smoothers in MG, respectively. As the solution space is often the dual of the data space in PDEs, the analogous concept of feature space and data space (which are dual to each other) is introduced in CNN. With such connections and new concept in the unified model, the function of various convolution operations and pooling used in CNN can be better understood. As a result, modified CNN models (with fewer weights and hyperparameters) are developed that exhibit competitive and sometimes better performance in comparison with existing CNN models when applied to both CIFAR-10 and CIFAR-100 data sets.
This is a preview of subscription content, to check access.
Barron A R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans Inform Theory, 1993, 39: 930–945
Bottou L, Curtis F E, Nocedal J. Optimization methods for large-scale machine learning. SIAM Rev, 2018, 60: 223–311
Chang B, Meng L, Haber E, et al. Multi-level residual networks from dynamical systems view. ArXiv:1710.10348, 2017
Chen Y, Li J, Xiao H, et al. Dual path networks. In: Advances in Neural Information Processing Systems, vol. 30. Long Beach: Neural Information Processing Systems Foundation, 2017, 4467–4475
Cybenko G. Approximation by superpositions of a sigmoidal function. Math Control Signals Systems, 1989, 2: 303–314
Deng J, Dong W, Socher R, et al. Imagenet: A large-scale hierarchical image database. In: Proceedings of the 2009 IEEE Conference on Computer Vision…
You can read the article in its entirety, on the official website of https://link.springer.com/article/10.1007/s11425-019-9547-2
Thanks a lot … I hope your thoughts, your geniuses can have as much resonance as possible.