Towards A Rigorous Science of Interpretable Machine Learning
As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningInterpretable Machine LearningPositionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On the Art and Science of Machine Learning Explanations
This text discusses several popular explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the explanatory methods are accepted tools of the trad…
BIG-bench Machine LearningInterpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
We present a brief history of the field of interpretable machine learning (IML), give an overview of state-of-the-art interpretation methods, and discuss challenges. Research in IML has boomed in recent years. As young a…
BIG-bench Machine LearningCausal InferenceInterpretable Machine LearningSensitivityQuantitative causality, causality-guided scientific discovery, and causal machine learning
It has been said, arguably, that causality analysis should pave a promising way to interpretable deep learning and generalization. Incorporation of causality into artificial intelligence (AI) algorithms, however, is chal…
scientific discoverySymbolic Foundation Regressor on Complex Networks
In science, we are interested not only in forecasting but also in understanding how predictions are made, specifically what the interpretable underlying model looks like. Data-driven machine learning technology can signi…
EpidemiologyregressionSymbolic RegressionHeliophysics Discovery Tools for the 21st Century: Data Science and Machine Learning Structures and Recommendations for 2020-2050
Three main points: 1. Data Science (DS) will be increasingly important to heliophysics; 2. Methods of heliophysics science discovery will continually evolve, requiring the use of learning technologies [e.g., machine lear…