paper-with-me

홈 › Papers

Universal approximation property of ODENet and ResNet with a single activation function

2024-10-22 · Masato Kimura, Kazunori Matsui, Yosuke Mizuno

We study a universal approximation property of ODENet and ResNet. The ODENet is a map from an initial value to the final value of an ODE system in a finite interval. It is considered a mathematical model of a ResNet-type deep learning system. We consider dynamical systems with vector fields given by a single composition of the activation function and an affine mapping, which is the most common choice of the ODENet or ResNet vector field in actual machine learning systems. We show that such an ODENet and ResNet with a restricted vector field can uniformly approximate ODENet with a general vector field.

📄 PDF Abstract BibTeX arXiv:2410.16709

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Average Pooling 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…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
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

Similar Papers 제목 키워드 기반

Universal Approximation Properties for an ODENet and a ResNet: Mathematical Analysis and Numerical Experiments

2020-12-22 · Yuto Aizawa, Masato Kimura, Kazunori Matsui

We prove a universal approximation property (UAP) for a class of ODENet and a class of ResNet, which are simplified mathematical models for deep learning systems with skip connections. The UAP can be stated as follows. L…

Binary ClassificationGeneral Classification

The Influence of the Memory Capacity of Neural DDEs on the Universal Approximation Property

2025-05-12 · Christian Kuehn, Sara-Viola Kuntz

Neural Ordinary Differential Equations (Neural ODEs), which are the continuous-time analog of Residual Neural Networks (ResNets), have gained significant attention in recent years. Similarly, Neural Delay Differential Eq…

Accelerating ODE-Based Neural Networks on Low-Cost FPGAs

2020-12-31 · Hirohisa Watanabe, Hiroki Matsutani

ODENet is a deep neural network architecture in which a stacking structure of ResNet is implemented with an ordinary differential equation (ODE) solver. It can reduce the number of parameters and strike a balance between…

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 wi…

On the approximation by single hidden layer feedforward neural networks with fixed weights

2017-08-21 · Namig J. Guliyev, Vugar E. Ismailov

Feedforward neural networks have wide applicability in various disciplines of science due to their universal approximation property. Some authors have shown that single hidden layer feedforward neural networks (SLFNs) wi…