Interpretable Machine Learning Model

Interpretable machine learning (IML) aims to create predictive models that are not only accurate but also transparent, allowing users to understand how decisions are reached. Current research focuses on developing IML models that maintain high predictive performance while offering insights into feature importance through techniques like additive models (including variations such as higher-order and structural versions), explainable boosting machines, and rule-based systems. This field is crucial for building trust and facilitating responsible use of AI in high-stakes applications like healthcare and engineering, where understanding model behavior is paramount for decision-making and accountability.

Papers

December 18, 2023

Perceptual Musical Features for Interpretable Audio Tagging
Vassilis Lyberatos, Spyridon Kantarelis, Edmund Dervakos, Giorgos Stamou
Inherent Interpretability Music Tagging Audio Tagging Interpretable Machine Learning Model

August 15, 2023

An Interpretable Machine Learning Model with Deep Learning-based Imaging Biomarkers for Diagnosis of Alzheimer's Disease
Wenjie Kang, Bo Li, Janne M. Papma, Lize C. Jiskoot, Peter Paul De Deyn, Geert Jan Biessels, Jurgen A. H. R. Claassen, Huub A. M. Middelkoop, Wiesje M. van der Flier, Inez H. G. B. Ramakers, Stefan Klein, Esther E. Bron
Alzheimer'S Disease Medical Diagnosis Common Disease Interpretable Machine Learning Generalized Additive Model Disease Neuroimaging Initiative Explainable Boosting Machine High Dimensional Imaging Interpretable Machine Learning Model Biomarker Image

February 18, 2023

Structural Neural Additive Models: Enhanced Interpretable Machine Learning
Mattias Luber, Anton Thielmann, Benjamin Säfken
Deep Neural Network Interpretable Neural Network Neural Additive Model Neural Network Application Interpretable Machine Learning Model

January 17, 2023

Explainable, Interpretable & Trustworthy AI for Intelligent Digital Twin: Case Study on Remaining Useful Life
Kazuma Kobayashi, Syed Bahauddin Alam
Machine Learning Artificial Intelligence Case Study Digital Twin Artificial Intelligence Model Trustworthy Artificial Intelligence Interpretable Way Useful Life Interpretable Machine Learning Model

September 30, 2022

Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions
Minkyu Kim, Hyun-Soo Choi, Jinho Kim
Black Box Model Interpretable Way Feature Interaction Interpretable Machine Neural Additive Model Interpretable Machine Learning Model

May 20, 2022

ExMo: Explainable AI Model using Inverse Frequency Decision Rules
Pradip Mainali, Ismini Psychoula, Fabien A. P. Petitcolas
Decision Relevant Information Decision Rule Explainable AI Model Probabilistic Rule Frequency Component Interpretable Machine Learning Model

November 23, 2021

Interpreting Machine Learning Models for Room Temperature Prediction in Non-domestic Buildings
Jianqiao Mao, Grammenos Ryan
Black Box Model Residential Building Interpretable Machine Learning Method Temperature Prediction Interpretable Machine Learning Model Interpretable Optimization

Interpretable Machine Learning Model

Papers

Perceptual Musical Features for Interpretable Audio Tagging

An Interpretable Machine Learning Model with Deep Learning-based Imaging Biomarkers for Diagnosis of Alzheimer's Disease

Structural Neural Additive Models: Enhanced Interpretable Machine Learning

Explainable, Interpretable & Trustworthy AI for Intelligent Digital Twin: Case Study on Remaining Useful Life

Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions

ExMo: Explainable AI Model using Inverse Frequency Decision Rules

Interpreting Machine Learning Models for Room Temperature Prediction in Non-domestic Buildings