Despite its great success, machine learning can have its limits when dealing
with insufficient training data. A potential solution is the additional
integration of prior knowledge into the training process which leads to the
notion of informed machine learning. In this paper, we present a structured
overview of various approaches in this field. We provide a definition and
propose a concept for informed machine learning which illustrates its building
blocks and distinguishes it from conventional machine learning. We introduce a
taxonomy that serves as a classification framework for informed machine
learning approaches. It considers the source of knowledge, its representation,
and its integration into the machine learning pipeline. Based on this taxonomy,
we survey related research and describe how different knowledge representations
such as algebraic equations, logic rules, or simulation results can be used in
learning systems. This evaluation of numerous papers on the basis of our
taxonomy uncovers key methods in the field of informed machine learning.
Description
[1903.12394] Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
%0 Generic
%1 vonrueden2019informed
%A von Rueden, Laura
%A Mayer, Sebastian
%A Beckh, Katharina
%A Georgiev, Bogdan
%A Giesselbach, Sven
%A Heese, Raoul
%A Kirsch, Birgit
%A Pfrommer, Julius
%A Pick, Annika
%A Ramamurthy, Rajkumar
%A Walczak, Michal
%A Garcke, Jochen
%A Bauckhage, Christian
%A Schuecker, Jannis
%D 2019
%K ai deep deeplearning knowledge learning machine ml survey taxonomy
%R 10.1109/TKDE.2021.3079836
%T Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
%U http://arxiv.org/abs/1903.12394
%X Despite its great success, machine learning can have its limits when dealing
with insufficient training data. A potential solution is the additional
integration of prior knowledge into the training process which leads to the
notion of informed machine learning. In this paper, we present a structured
overview of various approaches in this field. We provide a definition and
propose a concept for informed machine learning which illustrates its building
blocks and distinguishes it from conventional machine learning. We introduce a
taxonomy that serves as a classification framework for informed machine
learning approaches. It considers the source of knowledge, its representation,
and its integration into the machine learning pipeline. Based on this taxonomy,
we survey related research and describe how different knowledge representations
such as algebraic equations, logic rules, or simulation results can be used in
learning systems. This evaluation of numerous papers on the basis of our
taxonomy uncovers key methods in the field of informed machine learning.
@misc{vonrueden2019informed,
abstract = {Despite its great success, machine learning can have its limits when dealing
with insufficient training data. A potential solution is the additional
integration of prior knowledge into the training process which leads to the
notion of informed machine learning. In this paper, we present a structured
overview of various approaches in this field. We provide a definition and
propose a concept for informed machine learning which illustrates its building
blocks and distinguishes it from conventional machine learning. We introduce a
taxonomy that serves as a classification framework for informed machine
learning approaches. It considers the source of knowledge, its representation,
and its integration into the machine learning pipeline. Based on this taxonomy,
we survey related research and describe how different knowledge representations
such as algebraic equations, logic rules, or simulation results can be used in
learning systems. This evaluation of numerous papers on the basis of our
taxonomy uncovers key methods in the field of informed machine learning.},
added-at = {2021-06-30T14:21:46.000+0200},
author = {von Rueden, Laura and Mayer, Sebastian and Beckh, Katharina and Georgiev, Bogdan and Giesselbach, Sven and Heese, Raoul and Kirsch, Birgit and Pfrommer, Julius and Pick, Annika and Ramamurthy, Rajkumar and Walczak, Michal and Garcke, Jochen and Bauckhage, Christian and Schuecker, Jannis},
biburl = {https://www.bibsonomy.org/bibtex/2836e41fdf67954f455307b44af22e315/jaeschke},
description = {[1903.12394] Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems},
doi = {10.1109/TKDE.2021.3079836},
interhash = {a86cf7c1d8b09365a13d0363a9c549bb},
intrahash = {836e41fdf67954f455307b44af22e315},
keywords = {ai deep deeplearning knowledge learning machine ml survey taxonomy},
note = {cite arxiv:1903.12394Comment: Accepted at IEEE Transactions on Knowledge and Data Engineering: https://ieeexplore.ieee.org/document/9429985},
timestamp = {2021-06-30T14:21:46.000+0200},
title = {Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems},
url = {http://arxiv.org/abs/1903.12394},
year = 2019
}