zichuan-liu/TimeXplusplus
[ICML'24] Official PyTorch Implementation of TimeX++
This project helps domain experts understand why a deep learning model made a specific prediction on time series data. It takes your existing time series data and the predictions from your deep learning model, then highlights the crucial parts of the time series that led to that prediction. This is useful for scientists, engineers, or analysts who need clear, transparent insights from complex time series models.
No commits in the last 6 months.
Use this if you need to interpret the outputs of a deep learning model applied to time series data, especially in critical applications where understanding 'why' is as important as 'what'.
Not ideal if you are looking for a tool to train a new time series prediction model from scratch, as this focuses on explaining existing models.
Stars
30
Forks
5
Language
Python
License
—
Last pushed
Nov 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zichuan-liu/TimeXplusplus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...