NN2Rules: Extracting Rule List from Neural Networks

1 code implementation • 4 Jul 2022 • G Roshan Lal, Varun Mithal

NN2Rules is a decompositional approach to rule extraction, i. e., it extracts a set of decision rules from the parameters of the trained neural network model.

Decision Making Explainable artificial intelligence +1

TE2Rules: Explaining Tree Ensembles using Rules

2 code implementations • 29 Jun 2022 • G Roshan Lal, Xiaotong Chen, Varun Mithal

Tree Ensemble (TE) models, such as Gradient Boosted Trees, often achieve optimal performance on tabular datasets, yet their lack of transparency poses challenges for comprehending their decision logic.

Binary Classification Decision Making +2

Semi-supervised Classification using Attention-based Regularization on Coarse-resolution Data

no code implementations • 3 Jan 2020 • Guruprasad Nayak, Rahul Ghosh, Xiaowei Jia, Varun Mithal, Vipin Kumar

Many real-world phenomena are observed at multiple resolutions.

General Classification MULTI-VIEW LEARNING +2

An Attentive Survey of Attention Models

no code implementations • 5 Apr 2019 • Sneha Chaudhari, Varun Mithal, Gungor Polatkan, Rohan Ramanath

This survey provides a structured and comprehensive overview of the developments in modeling attention.