machinelearningnuremberg/WellTunedSimpleNets

[NeurIPS 2021] Well-tuned Simple Nets Excel on Tabular Datasets

42
/ 100
Emerging

This project helps machine learning researchers improve the performance of deep learning models on structured datasets, like those found in databases or spreadsheets. It takes your tabular data and, through a process of automatically combining various regularization techniques, produces a highly optimized simple neural network that often outperforms traditional methods and complex deep learning architectures. It's designed for ML researchers and data scientists focused on achieving state-of-the-art results with tabular data.

No commits in the last 6 months.

Use this if you are a machine learning researcher or data scientist struggling to get deep learning models to outperform traditional methods like XGBoost on tabular datasets and want to explore advanced regularization techniques.

Not ideal if you are looking for a plug-and-play solution for immediate deployment or if your primary interest is in non-tabular data types like images or text.

machine-learning-research tabular-data deep-learning-optimization hyperparameter-tuning data-science-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

88

Forks

16

Language

Python

License

Apache-2.0

Last pushed

Feb 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/machinelearningnuremberg/WellTunedSimpleNets"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.