Feature Subset Selection: 🎯 Optimize your data analysis! 🎯 By choosing the right features, we can eliminate redundancy and irrelevance, boosting accuracy and efficiency. Let's find the best subset! 🎯 #FeatureSelection #DataPrep #DataMining

https://towardsdatascience.com/data-preprocessing-in-data-mining-machine-learning-79a9662e2eb

"Composite Feature Selection Using Deep Ensembles" by Imrie et al. proposes a new group #FeatureSelection, in which an ensemble of *weak* feature selection methods works towards selecting smallest groups with a minimum overlapping. https://openreview.net/forum?id=-9PV7GKwYpM

"Everything should be made as simple as possible, but no simpler"

- Albert Einstein

#FeatureSelection methods can help providing simpler #MachineLearning models, but we need to make sure they are not more complicated than the induction method, nor the resulting models.

RT @pkgyawali@twitter.com

Check out our works on Knockoff Framework.

1. GhostKnockoff (@NatureComms@twitter.com)
2. Ensembling DL (https://arxiv.org/abs/2210.00604 at MLCB)

#Knockoff #FeatureSelection #interpretation https://twitter.com/NatureComms/status/1598258604833878017

🐦🔗: https://twitter.com/pkgyawali/status/1600354746203664385

📢📢📢 New #Paper: '#FeatureSelection with Distance Correlation' (https://arxiv.org/abs/2212.00046) - a short #PaperSummary thread

We investigates how to automatically find a small # of features that - when put into a simple #NeuralNetwork - yield good performance (e.g. for classification)

Two possible uses:
- Explain the behavior of a #BlackBox classifier
- Build a light-weight classifier from scratch