首页/数据集/Rapid Learning of Temporal Dependencies at Multiple Timescales

Rapid Learning of Temporal Dependencies at Multiple Timescales

NIAID Data Ecosystem2026-05-02 收录

时序学习机制

多尺度时序建模

数据链接：

https://doi.org/10.7910/DVN/GULYJP 数据链接链接失效反馈

官方服务：

资源简介：

Data and code associated with the paper: "Rapid Learning of Temporal Dependencies at Multiple Timescales."

应用场景：

创建时间：

2025-07-25

技术债务识别

时序学习机制

Automated identification of self-admitted technical debt (SATD) has been crucial for advancements in managing such debt. However, state-of-the-arts studies often overlook chronological factors, leadin

NIAID Data Ecosystem40

Data for the paper: Locally Weighted Least Squares Temporal Difference Learning

强化学习

时序学习机制

These data are associated with the evaluations presented in the paper: Locally Weighted Least Squares Temporal Difference Learning, Matthew Howard and Yoshihiko Nakamura, European Symposium on Artifi

NIAID Data Ecosystem20

Additional model parameters.

参数优化

时序学习机制

Eligibility trace (λ), stickiness (π), and inverse-temperature (β) parameters by study for Model 3. (XLSX)

NIAID Data Ecosystem20

Probabilistic associative learning suffices for learning the temporal structure of multiple sequences

时序学习机制

神经网络记忆模型

From memorizing a musical tune to navigating a well known route, many of our underlying behaviors have a strong temporal component. While the mechanisms behind the sequential nature of the underlying

Figshare2019-08-01 更新20

Additional model parameters.

参数优化

时序学习机制

Eligibility trace (λ), stickiness (π), and inverse-temperature (β) parameters by study for Model 3. (XLSX)

Figshare2022-12-19 更新20