Inherent Interpretability

Inherent interpretability in machine learning focuses on designing models and methods that are inherently transparent and understandable, aiming to reduce the "black box" nature of many AI systems. Current research emphasizes developing intrinsically interpretable model architectures, such as those based on decision trees, rule-based systems, and specific neural network designs (e.g., Kolmogorov-Arnold Networks), alongside techniques like feature attribution and visualization methods to enhance understanding of model behavior. This pursuit is crucial for building trust in AI, particularly in high-stakes applications like healthcare and finance, where understanding model decisions is paramount for responsible deployment and effective human-AI collaboration.

Papers

April 2, 2022

AutoProtoNet: Interpretability for Prototypical Networks
Pedro Sandoval-Segura, Wallace Lawson
Inherent Interpretability Shot Learning Meta Learning Prototypical Network

April 1, 2022

Explainable and Interpretable Diabetic Retinopathy Classification Based on Neural-Symbolic Learning
Se-In Jang, Michael J. A. Girard, Alexandre H. Thiery
Inherent Interpretability Diabetic Retinopathy Interpretable Representation Symbolic Representation Neural Symbolic Learning

March 30, 2022

March 28, 2022

Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking
Tianyi Luo, Rui Meng, Xin Eric Wang, Yang Liu
Inherent Interpretability Model Interpretability Replication Study Interpretable Text Classification

March 25, 2022

Preprocessing Reward Functions for Interpretability
Erik Jenner, Adam Gleave
Inherent Interpretability Reward Function Interpretability Tool

March 24, 2022

March 20, 2022

Interpretability of Fine-grained Classification of Sadness and Depression
Tiasa Singha Roy, Priyam Basu, Aman Priyanshu, Rakshit Naidu
Fine Grained Inherent Interpretability Underlying Emotion Experienced Emotion Depression Symptom Human Emotion

March 14, 2022

Interpretability for Language Learners Using Example-Based Grammatical Error Correction
Masahiro Kaneko, Sho Takase, Ayana Niwa, Naoaki Okazaki
Inherent Interpretability Grammatical Error Correction Language Learner

March 13, 2022

March 11, 2022

March 8, 2022

March 7, 2022

March 6, 2022

Towards a Responsible AI Development Lifecycle: Lessons From Information Security
Erick Galinkin
Inherent Interpretability High Explainability Critical Lesson Security Related Fairness Metric Threat Model

March 4, 2022

Interpretable Off-Policy Learning via Hyperbox Search
Daniel Tschernutter, Tobias Hatt, Stefan Feuerriegel
Inherent Interpretability Policy Learning Patient Data

Inherent Interpretability

Papers

AutoProtoNet: Interpretability for Prototypical Networks

Explainable and Interpretable Diabetic Retinopathy Classification Based on Neural-Symbolic Learning

Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning

Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis

Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking

Preprocessing Reward Functions for Interpretability

Interpretability of Neural Network With Physiological Mechanisms

Feature visualization for convolutional neural network models trained on neuroimaging data

Interpretability of Fine-grained Classification of Sadness and Depression

Interpretability for Language Learners Using Example-Based Grammatical Error Correction

Algebraic Learning: Towards Interpretable Information Modeling

Symbolic Learning to Optimize: Towards Interpretability and Scalability

REX: Reasoning-aware and Grounded Explanation

Interpretable machine learning in Physics

Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine

Policy Regularization for Legible Behavior

Clustering and classification of low-dimensional data in explicit feature map domain: intraoperative pixel-wise diagnosis of adenocarcinoma of a colon in a liver

Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks

Towards a Responsible AI Development Lifecycle: Lessons From Information Security

Interpretable Off-Policy Learning via Hyperbox Search