DeepAI AI Chat
Log In Sign Up

Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena

by   Timo Freiesleben, et al.

Interpretable machine learning (IML) is concerned with the behavior and the properties of machine learning models. Scientists, however, are only interested in the model as a gateway to understanding the modeled phenomenon. We show how to develop IML methods such that they allow insight into relevant phenomenon properties. We argue that current IML research conflates two goals of model-analysis – model audit and scientific inference. Thereby, it remains unclear if model interpretations have corresponding phenomenon interpretation. Building on statistical decision theory, we show that ML model analysis allows to describe relevant aspects of the joint data probability distribution. We provide a five-step framework for constructing IML descriptors that can help in addressing scientific questions, including a natural way to quantify epistemic uncertainty. Our phenomenon-centric approach to IML in science clarifies: the opportunities and limitations of IML for inference; that conditional not marginal sampling is required; and, the conditions under which we can trust IML methods.


Interpretable and Explainable Machine Learning for Materials Science and Chemistry

While the uptake of data-driven approaches for materials science and che...

Science through Machine Learning: Quantification of Poststorm Thermospheric Cooling

Machine learning (ML) is often viewed as a black-box regression techniqu...

Scientific intuition inspired by machine learning generated hypotheses

Machine learning with application to questions in the physical sciences ...

Interpretable machine learning: definitions, methods, and applications

Machine-learning models have demonstrated great success in learning comp...

Data Centred Intelligent Geosciences: Research Agenda and Opportunities, Position Paper

This paper describes and discusses our vision to develop and reason abou...

Thermodynamics of learning physical phenomena

Thermodynamics could be seen as an expression of physics at a high epist...

Neurosymbolic Programming for Science

Neurosymbolic Programming (NP) techniques have the potential to accelera...