- 综合排序
- 最热优先
- 最新优先
- 来自专栏深度学习与计算机视觉
Trajectory Forecasting：TrajNet++
aicrowd trajnet challenge Awesome Interaction-aware Behavior and Trajectory Prediction Human Trajectory Forecasting in Crowds:A Deep Learning Perspective TrajNet++: Large-scale Trajectory Forecasting Benchmark
77810编辑于 2021-12-07 - 来自专栏challenge filter
Temporal fusion transformers for interpretable multi-horizon time series forecasting
Temporal fusion transformers for interpretable multi-horizon time series forecasting 摘要 文章关注的是multi-horizon forecasting，这方面包含了很多的输入数据，包括static covariate，known future input，以及其他只在过去被观察到的外源时间序列（即没有它们如何与目标值交互的信息 （不太清楚static covariate到底是什么，听起来有点像是多变量时间序列预测） 传统的multi-horizon forecasting应用可以访问大量的数据源，包括未来已经知道的数据（比如假期的时间 3 Multi-horizon forecasting 时间序列预测的定义 4 Model Architecture 主要部件 Gating mechanism，用来跳过架构中没有使用的组件，提供一种自适应的深度和网络复杂度来应对不同的环境
1.1K10编辑于 2022-06-17 - 来自专栏challenge filter
Recurrent Neural Networks for Time Series Forecasting: Current status and future directions
Recurrent Neural Networks for Time Series Forecasting: Current status and future directions 2021 International Journal of Forecasting 文章对基于RNN的时间序列预测方法进行了比较全面地综述，而且这是发表在IJF上的文章，意味着这篇文章会更偏向于预测本身，而不是模型。 文章结构：第二部分是背景知识，包括传统univariate forecasting technique和不同的NN预测；第三部分包括RNN的实现细节和相关的数据预处理方法；第四部分解释了本文评测时所用的方法与数据集 第二部分 2.1 Univariate Forecasting 传统的单变量方法即为时间序列基于其过去的值来完成对未来值的预测，即给定序列X={x1,x2,…,xT}，需要完成{X_{T+1},…,X_
40010编辑于 2022-06-17 - 来自专栏DeepHub IMBA
PyTorch-Forecasting一个新的时间序列预测库
PyTorch- forecasting是一个建立在PyTorch之上的开源Python包，专门用于简化和增强时间序列的工作。 在本文中我们介绍PyTorch-Forecasting的特性和功能，并进行示例代码演示。 PyTorch-Forecasting的安装非常简单： pip install pytorch-forecasting 但是需要注意的是，他目前现在只支持Pytorch 1.7以上，但是2.0是否支持我没有测试 PyTorch-Forecasting提供了几个方面的功能： 1、提供了一个高级接口，抽象了时间序列建模的复杂性，可以使用几行代码来定义预测任务，使得使用不同的模型和技术进行实验变得容易。 有兴趣的看看官方的文档和代码示例: https://pytorch-forecasting.readthedocs.io/en/stable/index.html
98710编辑于 2023-08-28 - 来自专栏机器学习原理
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting(论文阅读02)
我们在两个现实世界的大规模数据集上进行了实验：（1）METR-LA此交通数据集包含从洛杉矶县高速公路上的环路检测器收集的交通信息（Jagadish等，2014）。我们选择了207个传感器，并收集了从2012年3月1日到2012年6月30日的4个月的数据进行实验。 （2）PEMS-BA Y该交通数据集由加利福尼亚州运输机构（CalTrans）绩效评估系统（PeMS）收集。我们在湾区选择了325个传感器，并收集了从2017年1月1日到2017年5月31日的6个月数据进行实验
1.8K30发布于 2020-12-21 - 来自专栏DeepHub IMBA
Kaggle M5 Forecasting:传统预测方法与机器学习预测方法对比
本文使用的数据集来自 kaggle：M5 Forecasting — Accuracy。该数据集包含有 California、Texas、Wisconsin 三个州的产品类别、部门、仓储信息等。 本文代码：https://github.com/Deffro/Data-Science-Portfolio/tree/master/Notebooks/Forecasting%20Wars%20-%20Classical %20Forecasting%20Methods%20vs%20Machine%20Learning 作者：Dimitris Effrosynidis deephub翻译组： Oliver Lee DeepHub
2.2K10发布于 2020-05-09 - 来自专栏从流域到海域
How to Save an ARIMA Time Series Forecasting Model in Python (如何在Python中保存ARIMA时间序列预测模型)
How to Save an ARIMA Time Series Forecasting Model in Python 原文作者：Jason Brownlee 原文地址：https://machinelearningmastery.com /save-arima-time-series-forecasting-model-python/ 译者微博：@从流域到海域 译者博客：blog.csdn.net/solo95 如何在Python
2.6K100发布于 2018-02-05 - 来自专栏数据拾光者
广告行业中那些趣事系列51：超牛的kaggle比赛Favorita Grocery Sales Forecasting冠军方案
本篇分享了kaggle比赛《Corporación Favorita Grocery Sales Forecasting》冠军方案,对商品销量预测相关问题感兴趣的小伙伴可以一起沟通交流。 摘要：本篇分享了kaggle比赛《Corporación Favorita Grocery Sales Forecasting》冠军方案。 下面主要按照如下思维导图进行学习分享： 01 比赛介绍及数据理解 最近因为工作原因需要调研下kaggle比赛《Corporación Favorita Grocery Sales Forecasting 该比赛kaggle地址如下： https://www.kaggle.com/c/favorita-grocery-sales-forecasting/overview 整体来看该比赛就是预测商品的销量， 02 详解冠军方案 冠军方案介绍地址如下： https://www.kaggle.com/c/favorita-grocery-sales-forecasting/discussion/47582 2.1
81720编辑于 2022-05-05 - 来自专栏时空探索之旅
AAAI 2026 | 时间序列(Time Series) 论文总结[上] (Oral+预测)
ReCast: Reliability-aware Codebook-assisted Lightweight Time Series Forecasting2. Goal-Oriented Time-Series Forecasting: FoundationFramework Design10. FeTS: A Feature-Aware Framework for Time Series Forecasting22. HN-MVTS: HyperNetwork-based Multivariate Time Series Forecasting30. Harmonic Dataset Distillation for Time Series Forecasting33.
25310编辑于 2026-03-10 - 来自专栏时空探索之旅
IJCAI 2025 | 时间序列(Time Series)论文总结
Non-collective Calibrating Strategy for Time Series Forecasting 4. TCDM: A Temporal Correlation-Empowered Diffusion Model for Time Series Forecasting 5. Conditional Information Bottleneck-Based Multivariate Time Series Forecasting 9. FreqLLM: Frequency-Aware Large Language Models for Time Series Forecasting 16. CRAFT: Time Series Forecasting with Cross-Future Behavior Awareness 18.
1.1K10编辑于 2025-07-24 - 来自专栏GiantPandaCV
时间序列预测paper、应用汇总
- a two-fold approach for lumpy and intermittent demand（2021） 06 CNN用于时序预测 Probabilistic forecasting (2021) Deep Factors for Forecasting(2019) Deep State Space Models for Time Series Forecasting(2018) N-BEATS ,Neural basis expansion analysis for interpretable time series forecasting(2020) 09 Transformer用于时序预测 Informer-Beyond Efficient Transformer for Long Sequence Time-Series Forecasting(2020) Temporal Fusion Transformers for interpretable multi-horizon time series forecasting(2021) enhancing-the-locality-and-breaking-the-memory-bottleneck-of-transformer-on-time-series-forecasting-Paper
51350编辑于 2022-09-28 - 来自专栏Windows技术交流
System Data Archiver和System-Insights
storage consumption forecasting – Forecasts total storage consumption across all local drives.Volume consumption forecasting – Forecasting storage consumption for each volume.System Data Archiver是System-Insights storage consumption forecasting – Forecasts total storage consumption across all local drives.Volume consumption forecasting – Forecasting storage consumption for each volume.CPU 容量预测 – 预测 CPU 使用率网络容量预测 and then show the results of "CPU capacity forecasting."
1.2K40编辑于 2022-09-29 - 来自专栏时空探索之旅
WWW 2026 | 时间序列（Time Series）论文总结（预测，生成，插补，分类，异常检测等）
Cross-city Time Series Forecasting with Retrieval-Augmented Large Language Models4. Automated Model Selection for Multivariate Time Series Forecasting6. Dynamic Multi-period Experts for Online Time Series Forecasting8. FedRMamba: Federated Residual Mamba for Multivariate Time-Series Forecasting12. QuiZSF: A Retrieval-Augmented Framework for Zero-Shot Time Series Forecasting13.
10810编辑于 2026-03-10 - 来自专栏时空探索之旅
ICLR 2026 | 时间序列（Time Series）论文总结（上）【预测，多模态，预测×LLM，基础模型】
Numerion: A Multi-Hypercomplex Model for Time Series Forecasting6. Scalable Time Series Forecasting via Local Cross-Variate Modeling13. ResCP: Reservoir Conformal Prediction for Time Series Forecasting14. TEDM: Time Series Forecasting with Elucidated Diffusion Models22. Semantic-Enhanced Time-Series Forecasting via Large Language Models35.
37410编辑于 2026-03-10 - 来自专栏时空探索之旅
ICLR 2025 | 时间序列(Time Series)高分论文总结
Investigating Pattern Neurons in Urban Time Series Forecasting Locally Connected Echo State Networks Multivariate Time Series Forecasting TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series id=e1wDDFmlVu 分数：688 关键词：预测，基础模型，混合专家系统 keywords：time series, foundation model, forecasting Time-MoE performance. 6 Fast and Slow Streams for Online Time Series Forecasting Without Information Leakage 22 Investigating Pattern Neurons in Urban Time Series Forecasting 链接：https://openreview.net/forum?
3.8K13编辑于 2024-12-19 - 来自专栏贾志刚-OpenCV学堂
【建议收藏】时间序列预测paper、应用汇总
- a two-fold approach for lumpy and intermittent demand（2021） 06 CNN用于时序预测 Probabilistic forecasting (2021) Deep Factors for Forecasting(2019) Deep State Space Models for Time Series Forecasting(2018) N-BEATS ,Neural basis expansion analysis for interpretable time series forecasting(2020) 09 Transformer用于时序预测 Informer-Beyond Efficient Transformer for Long Sequence Time-Series Forecasting(2020) Temporal Fusion Transformers for interpretable multi-horizon time series forecasting(2021) enhancing-the-locality-and-breaking-the-memory-bottleneck-of-transformer-on-time-series-forecasting-Paper
56410编辑于 2022-08-29 - 来自专栏贾志刚-OpenCV学堂
【建议收藏】时间序列预测应用、paper汇总
- a two-fold approach for lumpy and intermittent demand（2021） 06 CNN用于时序预测 Probabilistic forecasting (2021) Deep Factors for Forecasting(2019) Deep State Space Models for Time Series Forecasting(2018) N-BEATS ,Neural basis expansion analysis for interpretable time series forecasting(2020) 09 Transformer用于时序预测 Informer-Beyond Efficient Transformer for Long Sequence Time-Series Forecasting(2020) Temporal Fusion Transformers for interpretable multi-horizon time series forecasting(2021) enhancing-the-locality-and-breaking-the-memory-bottleneck-of-transformer-on-time-series-forecasting-Paper
1K40编辑于 2022-06-24 - 来自专栏时空探索之旅
NeurIPS 2024 | 时间序列（Time Series）论文总结
7，10，24，52 基础模型：16，29，35，53 扩散模型：1，31，42，43 1 Retrieval-Augumented Diffusion Models for Time Series Forecasting Liu, Ling Yang, Hongyan Li, Shenda Hong 关键词：预测，扩散模型，检索增强 2 Attractor Memory for Long-Term Time Series Forecasting , Dongliang Cui 关键词：预测，多尺度，超图，Transformer 4 FilterNet: Harnessing Frequency Filters for Time Series Forecasting 去掉预训练LLM效果反而提升 11 Rethinking Fourier Transform for Long-term Time Series Forecasting: A Basis Functions Decomposition Delivers Both in Long-term Time Series Forecasting 链接：https://neurips.cc/virtual/2024/poster
2.2K10编辑于 2024-11-19 - 来自专栏好奇心Log
算法比赛 | KDD Cup2022 风力发电预测比赛总结
赛题介绍 空间动态风力发电预测（Spatial Dynamic Wind Power Forecasting）对风能的利用具有实际意义，参与者应准确估计风电场的风能供应。 赛题背景 风电预测（Wind Power Forecasting, WPF）旨在准确估计风电场在不同时间尺度上的风能供应。风电是一种清洁安全的可再生能源，但不能持续生产，导致高波动性。 pdf slides: https://baidukddcup2022.github.io/slides/hik.pdf Solution to Spatial Dynamic Wind Power Forecasting slides : https://baidukddcup2022.github.io/slides/didadida_hualahuala.pdf KDD CUP 2022 Wind Power Forecasting /github.com/injadlu/KDDCUP2022 BUAA_BIGSCity: Spatial-Temporal Graph Neural Network for Wind Power Forecasting
4.2K40编辑于 2022-11-15 - 来自专栏日常学python
sktime，一个高级的 Python 库！
from sktime.forecasting.compose import TransformedTargetForecaster from sktime.forecasting.exp_smoothing from sktime.forecasting.model_selection import temporal_train_test_split from sktime.forecasting.model_selection import pandas as pd from sktime.datasets import load_airline from sktime.forecasting.model_selection import pandas as pd from sktime.datasets import load_longley from sktime.forecasting.model_selection import temporal_train_test_split from sktime.forecasting.compose import ReducedRegressionForecaster
65810编辑于 2024-04-24
腾讯云开发者
Copyright © 2013 - 2026 Tencent Cloud. All Rights Reserved. 腾讯云 版权所有
深圳市腾讯计算机系统有限公司 ICP备案/许可证号：粤B2-20090059 
粤公网安备44030502008569号
腾讯云计算（北京）有限责任公司 京ICP证150476号 | 京ICP备11018762号