juno-hwang/juno-dkt
Scikit-learn style implementation of Deep Knowledge Tracing models based on pytorch.
This tool helps educators and learning scientists understand how student knowledge evolves over time as they answer questions or complete tasks. You provide student performance data (student IDs, item IDs, and correctness scores), and it outputs predictions of future performance and a knowledge graph showing relationships between learning items. It's designed for researchers or data analysts in educational settings.
No commits in the last 6 months. Available on PyPI.
Use this if you need to analyze student learning patterns and predict future performance based on their sequence of responses to educational items.
Not ideal if you don't have sequential student interaction data with distinct learning items, or if you're looking for a simple pass/fail assessment rather than a nuanced understanding of knowledge progression.
Stars
15
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 27, 2022
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/juno-hwang/juno-dkt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
kk7nc/RMDL
RMDL: Random Multimodel Deep Learning for Classification
OML-Team/open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
miguelvr/dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
PaddlePaddle/models
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models...