<aside> 💡 설명 가능한 인공지능(Explainable AI)에 대하여 공부하며 얻은 내용을 정리

</aside>

설명 가능한 인공지능이란?

What is Explainable AI

관련 논문

Causal Shapley Values - Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models

Consistent feature attribution for tree ensembles

Explainable AI - current status and future directions

Explainable AI-A Review of Machine Learning Interpretability Methods

N-BEATS-Neural Basis Expanation Analysis for Interpretable Time Series Forecasting

Opportunities and Challengers in Explainable Artificial Intelligence (XAI) - A Survey

Peeking Inside the Black Box(Visualizing)

To trust or not to trust an explanation-using LEAF to evaluate local linear XAI methods

방법론 소개

PDP(Partial Dependence Plot)

SHAP(SHapley Additive exPlanations)

LIME(Local Interpretable Model-agnostic Explanations)

추가 공부 자료

Interpretable Machine Learning

Hands-On Explainable AI (XAI) with Python Interpret, visualize, explain, and integrate reliable AI for fair, secure, and trustworthy AI apps by Denis Rothman

Explainable and Interpretable Models in Computer Vision and Machine Learning

📚 XAI 활용 연구

• 진공학회 포스터 논문

Loading Google Slides

• 수질 데이터 분석 연구 논문

Interpretation of ensemble learning to predict water quality using explainable artificial intelligence

• 머신러닝 기반의 교통 데이터 분석 및 설명가능한 AI 기반 결과 해석 연구

<aside> 📝 교통 데이터 분석 연구

</aside>

• 냄새 데이터 기반 복합악취 분석 연구 논문

Prediction of Complex Odor from Pig Barn Using Machine Learning and Identifying the Influence of Variables Using Explainable Artificial Intelligence