paper-with-me

Papers

MorphoActivation: Generalizing ReLU activation function by mathematical morphology

2022-07-13 · Santiago Velasco-Forero, Jesús Angulo

This paper analyses both nonlinear activation functions and spatial max-pooling for Deep Convolutional Neural Networks (DCNNs) by means of the algebraic basis of mathematical morphology. Additionally, a general family of activation functions is proposed by considering both max-pooling and nonlinear operators in the context of morphological representations. Experimental section validates the goodness of our approach on classical benchmarks for supervised learning by DCNN.

📄 PDF Abstract BibTeX arXiv:2207.06413

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

DCNN Diffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations…

Similar Papers 제목 키워드 기반

APTx: better activation function than MISH, SWISH, and ReLU's variants used in deep learning

2022-09-10 · Ravin Kumar

Activation Functions introduce non-linearity in the deep neural networks. This nonlinearity helps the neural networks learn faster and efficiently from the dataset. In deep learning, many activation functions are develop…

Deep Learning

Convergence of Deep ReLU Networks

2021-07-27 · Yuesheng Xu, Haizhang Zhang

We explore convergence of deep neural networks with the popular ReLU activation function, as the depth of the networks tends to infinity. To this end, we introduce the notion of activation domains and activation matrices…

image-classificationImage Classification

Convergence of Deep Neural Networks with General Activation Functions and Pooling

2022-05-13 · Wentao Huang, Yuesheng Xu, Haizhang Zhang

Deep neural networks, as a powerful system to represent high dimensional complex functions, play a key role in deep learning. Convergence of deep neural networks is a fundamental issue in building the mathematical founda…

Neuro-Symbolic Activation Discovery: Transferring Mathematical Structures from Physics to Ecology for Parameter-Efficient Neural Networks

2026-01-10 · Anas Hajbi arxiv

Modern neural networks rely on generic activation functions (ReLU, GELU, SiLU) that ignore the mathematical structure inherent in scientific data. We propose Neuro-Symbolic Activation Discovery, a framework that uses Gen…

Generalized Activation via Multivariate Projection

2023-09-29 · Jiayun Li, Yuxiao Cheng, Yiwen Lu, Zhuofan Xia 외

Activation functions are essential to introduce nonlinearity into neural networks, with the Rectified Linear Unit (ReLU) often favored for its simplicity and effectiveness. Motivated by the structural similarity between …