paper-with-me

Papers

Exploring the Relationship: Transformative Adaptive Activation Functions in Comparison to Other Activation Functions

2024-02-14 · Vladimír Kunc

Neural networks are the state-of-the-art approach for many tasks and the activation function is one of the main building blocks that allow such performance. Recently, a novel transformative adaptive activation function (TAAF) allowing for any vertical and horizontal translation and scaling was proposed. This work sets the TAAF into the context of other activation functions. It shows that the TAAFs generalize over 50 existing activation functions and utilize similar concepts as over 70 other activation functions, underscoring the versatility of TAAFs. This comprehensive exploration positions TAAFs as a promising and adaptable addition to neural networks.

📄 PDF Abstract BibTeX arXiv:2402.09249

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Similar Papers 제목 키워드 기반

Adaptively Customizing Activation Functions for Various Layers

2021-12-17 · Haigen Hu, Aizhu Liu, Qiu Guan, Xiaoxin Li 외

To enhance the nonlinearity of neural networks and increase their mapping abilities between the inputs and response variables, activation functions play a crucial role to model more complex relationships and patterns in …

Graph-Adaptive Activation Functions for Graph Neural Networks

2020-09-14 · Bianca Iancu, Luana Ruiz, Alejandro Ribeiro, Elvin Isufi

Activation functions are crucial in graph neural networks (GNNs) as they allow defining a nonlinear family of functions to capture the relationship between the input graph data and their representations. This paper propo…

Recommendation Systems

TraNCE: Transformative Non-linear Concept Explainer for CNNs

2025-03-26 · Ugochukwu Ejike Akpudo, Yongsheng Gao, Jun Zhou, Andrew Lewis

Convolutional neural networks (CNNs) have succeeded remarkably in various computer vision tasks. However, they are not intrinsically explainable. While the feature-level understanding of CNNs reveals where the models loo…

Adaptive Blending Units: Trainable Activation Functions for Deep Neural Networks

2018-06-26 · Leon René Sütfeld, Flemming Brieger, Holger Finger, Sonja Füllhase 외

The most widely used activation functions in current deep feed-forward neural networks are rectified linear units (ReLU), and many alternatives have been successfully applied, as well. However, none of the alternatives h…

Investigating the interaction between gradient-only line searches and different activation functions

2020-02-23 · D. Kafka, Daniel. N. Wilke

Gradient-only line searches (GOLS) adaptively determine step sizes along search directions for discontinuous loss functions resulting from dynamic mini-batch sub-sampling in neural network training. Step sizes in GOLS ar…