Comparative Performance Summary of Different Activation Functions.

Figshare2025-05-09 更新2026-04-28 收录

数据链接：

https://figshare.com/articles/dataset/Comparative_Performance_Summary_of_Different_Activation_Functions_/28998398 数据链接链接失效反馈

官方服务：

资源简介：

Comparative Performance Summary of Different Activation Functions.

创建时间：

2025-05-09

神经网络演示系统开发以及与原型系统的联合调试的数据集

内存计算加速器

神经网络优化

本数据集共包四篇神经网络演示系统开发以及与原型系统的联合调试相关论文的试验数据。分别是（GAS: General-Purpose In-Memory-Computing Accelerator for Sparse Matrix Multiplication）数据来源于模拟和数字电路仿真程序，使用文中提及的器件模型，阵列规模和外围电路设计，通过Hspice和Design Compiler分别对GA

国家基础学科公共科学数据中心130

sj-mat-3-ade-10.1177_16878132231175002 – Supplemental material for Optimization of Neural Network architecture and derivation of closed-form equation to predict ultimate load of functionally graded material plate

材料性能预测

神经网络优化

Supplemental material, sj-mat-3-ade-10.1177_16878132231175002 for Optimization of Neural Network architecture and derivation of closed-form equation to predict ultimate load of functionally graded mat

DataCite Commons2024-08-28 更新80

MSE and training time of training set and cross-validation set at different hidden neuron size.

神经网络优化

性能评估

MSE and training time of training set and cross-validation set at different hidden neuron size.

Figshare2021-02-22 更新40

Best neural network model features for predicting the different outcomes, determined by testing different combinations of activation functions, number of layers, and number of neurons per layer for each data set.

神经网络优化

参数优化

NIAID Data Ecosystem80

Comparison of Softmax with other activation functions.

深度学习优化