Comments (2)
感谢您的关注,基于FFN建模时间点关联可以结合自回归模型(AR)理解,时间点的滞后期和参数权重的位置是绑定的。然而,如果时间维度用Transformer建模,不加入位置编码时,模型对输入的Temporal Token是Permutation-invariant的
![image](https://private-user-images.githubusercontent.com/39073236/333518921-e9af1d48-8776-490c-89cb-c39c9ccd07ff.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.T3_b4z0RLqyHxHmAORxV8WReOznYrolbarRsFWYjoBw)
from itransformer.
感谢您的关注,基于FFN建模时间点关联可以结合自回归模型(AR)理解,时间点的滞后期和参数权重的位置是绑定的。然而,如果时间维度用Transformer建模,不加入位置编码时,模型对输入的Temporal Token是Permutation-invariant的
![]()
感谢您的回复
from itransformer.
Related Issues (20)
- 关于模型示意图的问题 HOT 2
- got killed HOT 1
- Multi-Label Prediction HOT 3
- 代码疑问 exp_long_term_forecasting.py HOT 1
- Why the results of PatchTST in iTransformer paper are worse than those in PatchTST paper? HOT 3
- 代码问题 HOT 5
- 关于变量关联分析图的问题 HOT 3
- Encoder-Decoder Architecture Issues HOT 3
- 预测曲线问题 HOT 3
- 尝试复现和改进时结果出现问题 HOT 2
- ValueError: non-broadcastable output operand with shape (3,1) doesn't match the broadcast shape (3,5) HOT 1
- 能否提供一下PEMS所有数据集的96步长预测结果 HOT 2
- 交通数据复现 HOT 1
- 自回归任务问题的请教 HOT 2
- 关于预测值与真实值的问题
- Using Custom Dataset with Different Input Lengths for Model
- How can i predict multivariate with multivariate HOT 2
- what is the 'label_len' in dataloader for? HOT 1
- Mixed frequency forecast with iTransformer?
- When will the TimeXer code be released?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from itransformer.