首页/数据集/Experimentation results of ConvLSTM with 32-Filters.

Experimentation results of ConvLSTM with 32-Filters.

Figshare2023-02-09 更新2026-04-28 收录

时序预测

深度学习评估

数据链接：

https://figshare.com/articles/dataset/Experimentation_results_of_ConvLSTM_with_32-Filters_/22062961 数据链接链接失效反馈

官方服务：

资源简介：

Experimentation results of ConvLSTM with 32-Filters.

应用场景：

创建时间：

2023-02-09

相关数据集

mMARCO

多语言信息检索

深度学习评估

mMARCO是一个多语言版本的MS MARCO段落排序数据集，由坎皮纳斯大学神经网络实验室创建，包含13种语言。该数据集通过机器翻译创建，旨在解决非英语语言在信息检索任务中训练资源稀缺的问题。数据集包含超过53万条查询-段落相关对，适用于训练和评估深度学习模型。mMARCO的创建不仅丰富了多语言信息检索的训练资源，还通过零样本学习场景的评估，展示了其对提升模型效果的潜力。

arXiv2022-08-18 更新1120

Performance and recource comparison of various structure of AEs.

自编码器架构比较

深度学习评估

Performance and recource comparison of various structure of AEs.

Figshare2018-03-16 更新90

Forecasting error (via RMSE) of various models and features using the Twitter dataset.

时序预测

社交媒体数据建模

The models used include VARMA and SVR, whereas the features used include the raw social dynamics (Baseline), level-1 activation vectors (H1), level-2 activation vectors (H2), and both levels of activa

NIAID Data Ecosystem80

Performance of feature maps obtained with DenseNet121.

图像特征提取

深度学习评估

Performance of feature maps obtained with DenseNet121.

Figshare2026-01-16 更新100

Performances of deep models on the 5 art periods.

风格分类

深度学习评估

Performances of deep models on the 5 art periods.

NIAID Data Ecosystem90