Error bounds for approximations using multichannel deep convolutional neural networks with downsampling
Summary: Deep learning with specific network topologies has been successfully applied in many fields. However, what is primarily called into question by people is its lack of theoretical foundation investigations, especially for structured neural networks. This paper theoretically studies the multichannel deep convolutional neural networks equipped with the downsampling operator, which is frequently used in applications. The results show that the proposed networks have outstanding approximation and generalization ability of functions from ridge class and Sobolev space. Not only does it answer an open and crucial question of why multichannel deep convolutional neural networks are universal in learning theory, but it also reveals the convergence rates.
- 0n the best approximation by ridge functions in the uniform norm
- Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With <inline-formula> <tex-math notation="LaTeX">$\ell^1$ </tex-math> </inline-formula> and <inline-formula>
- Approximation by Ridge Functions and Neural Networks
- Approximation by superpositions of a sigmoidal function
- Butterfly-net: optimal function representation based on convolutional neural networks
- Deep distributed convolutional neural networks: universality
- Deep learning
- Equivalence of approximation by convolutional neural networks and fully-connected networks
- Error bounds for approximations with deep ReLU networks
- scientific article; zbMATH DE number 1405266 (Why is no real title available?)
- Interpreting the basis path set in neural networks
- Lane departure assistance coordinated control system for in-wheel motor drive vehicles based on dynamic extension boundary decision
- Multilayer feedforward networks are universal approximators
- Neural networks and the best trigomometric approximation
- Nonlinear approximation and (deep) ReLU networks
- On the near optimality of the stochastic approximation of smooth functions by neural networks
- Theory of deep convolutional neural networks: downsampling
- Universal approximation bounds for superpositions of a sigmoidal function
- Universality of deep convolutional neural networks
- Wide-band butterfly network: stable and efficient inversion via multi-frequency neural networks
- Learning in the machine: to share or not to share?
- Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space
- Theory of deep convolutional neural networks: downsampling
- Universality of deep convolutional neural networks
- Convolutional neural networks analyzed via convolutional sparse coding
- Error Analysis and Improving the Accuracy of Winograd Convolution for Deep Neural Networks
- Statistical guarantees for regularized neural networks
- A Study on Affine Transformations and a Novel Universal Prediction Theory
- Convergence analysis for over-parameterized deep learning
- How can deep neural networks fail even with global optima?
This page was built for publication: Error bounds for approximations using multichannel deep convolutional neural networks with downsampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6155792)
