paper-with-me

홈 › Papers

Approximation Properties of Deep ReLU CNNs

2021-09-01 · Juncai He, Lin Li, Jinchao Xu

This paper focuses on establishing $L^2$ approximation properties for deep ReLU convolutional neural networks (CNNs) in two-dimensional space. The analysis is based on a decomposition theorem for convolutional kernels with a large spatial size and multi-channels. Given the decomposition result, the property of the ReLU activation function, and a specific structure for channels, a universal approximation theorem of deep ReLU CNNs with classic structure is obtained by showing its connection with one-hidden-layer ReLU neural networks (NNs). Furthermore, approximation properties are obtained for one version of neural networks with ResNet, pre-act ResNet, and MgNet architecture based on connections between these networks.

📄 PDF Abstract BibTeX arXiv:2109.00190

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Kaiming Initialization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Higher Order Approximation Rates for ReLU CNNs in Korobov Spaces

2025-01-20 · Yuwen Li, Guozhi Zhang

This paper investigates the $L_p$ approximation error for higher order Korobov functions using deep convolutional neural networks (CNNs) with ReLU activation. For target functions having a mixed derivative of order m+1 i…

Approximation speed of quantized vs. unquantized ReLU neural networks and beyond

2022-05-24 · Antoine Gonon, Nicolas Brisebarre, Rémi Gribonval, Elisa Riccietti

We deal with two complementary questions about approximation properties of ReLU networks. First, we study how the uniform quantization of ReLU networks with real-valued weights impacts their approximation properties. We …

Quantization

On the Depth of Monotone ReLU Neural Networks and ICNNs

2025-05-09 · Egor Bakaev, Florestan Brunck, Christoph Hertrich, Daniel Reichman 외

We study two models of ReLU neural networks: monotone networks (ReLU$^+$) and input convex neural networks (ICNN). Our focus is on expressivity, mostly in terms of depth, and we prove the following lower bounds. For the …

Expressivity and Approximation Properties of Deep Neural Networks with ReLU$^k$ Activation

2023-12-27 · Juncai He, Tong Mao, Jinchao Xu

In this paper, we investigate the expressivity and approximation properties of deep neural networks employing the ReLU$^k$ activation function for $k \geq 2$. Although deep ReLU networks can approximate polynomials effec…

Optimal rates of approximation by shallow ReLU$^k$ neural networks and applications to nonparametric regression

2023-04-04 · Yunfei Yang, Ding-Xuan Zhou

We study the approximation capacity of some variation spaces corresponding to shallow ReLU$^k$ neural networks. It is shown that sufficiently smooth functions are contained in these spaces with finite variation norms. Fo…

regression