Geodesic
Machine learning with probabilistic law discovery: a concise introduction
The Bulletin of Irkutsk State University. Series Mathematics, Tome 43 (2023), pp. 91-109 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

Probabilistic Law Discovery (PLD) is a logic based Machine Learning method, which implements a variant of probabilistic rule learning. In several aspects, PLD is close to Decision Tree/Random Forest methods, but it differs significantly in how relevant rules are defined. The learning procedure of PLD solves the optimization problem related to the search for rules (called probabilistic laws), which have a minimal length and relatively high probability. At inference, ensembles of these rules are used for prediction. Probabilistic laws are human-readable and PLD based models are transparent and inherently interpretable. Applications of PLD include classification/clusterization/regression tasks, as well as time series analysis/anomaly detection and adaptive (robotic) control. In this paper, we outline the main principles of PLD, highlight its benefits and limitations and provide some application guidelines.
Keywords: probabilistic rule learning, knowledge discovery, interpretable machine learning. 
@article{IIGUM_2023_43_a6,
     author = {Alexander V. Demin and Denis K. Ponomaryov},
     title = {Machine learning with probabilistic law discovery: a concise introduction},
     journal = {The Bulletin of Irkutsk State University. Series Mathematics},
     pages = {91--109},
     year = {2023},
     volume = {43},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/IIGUM_2023_43_a6/}
}
TY  - JOUR
AU  - Alexander V. Demin
AU  - Denis K. Ponomaryov
TI  - Machine learning with probabilistic law discovery: a concise introduction
JO  - The Bulletin of Irkutsk State University. Series Mathematics
PY  - 2023
SP  - 91
EP  - 109
VL  - 43
UR  - http://geodesic.mathdoc.fr/item/IIGUM_2023_43_a6/
LA  - en
ID  - IIGUM_2023_43_a6
ER  - 
%0 Journal Article
%A Alexander V. Demin
%A Denis K. Ponomaryov
%T Machine learning with probabilistic law discovery: a concise introduction
%J The Bulletin of Irkutsk State University. Series Mathematics
%D 2023
%P 91-109
%V 43
%U http://geodesic.mathdoc.fr/item/IIGUM_2023_43_a6/
%G en
%F IIGUM_2023_43_a6
Alexander V. Demin; Denis K. Ponomaryov. Machine learning with probabilistic law discovery: a concise introduction. The Bulletin of Irkutsk State University. Series Mathematics, Tome 43 (2023), pp. 91-109. http://geodesic.mathdoc.fr/item/IIGUM_2023_43_a6/

[1] Demin A. V., “Data Clusterization with the Logic Probabilistic Approach to Knowledge Discovery”, Information Technology in the Humanities, 21 (2015), 28–33 (in Russian)

[2] Demin A. V., “Deep Learning of Adaptive Control Systems Based on a Logical-probabilistic Approach”, Bulletin of Irkutsk State University, Series Mathematics, 38 (2021), 65–83 | DOI

[3] Demin A. V., “Adaptive Locomotion Control System for Robots with Arbitrarily Modular Design”, Procedia Computer Science, 169 (2020), 829–834 | DOI

[4] Demin A. V. and Ponomaryov D. K., “Interpretable Reinforcement Learning with Multilevel Subgoal Discovery”, Proc. 21st International Conference on Machine Learning and Applications (ICMLA) (Nassau, Bahamas, 2022) | DOI

[5] Demin A. V., Vityaev E. E., “Relational Approach to Knowledge Discovery and its Applications”, Proc. ZONT Conference, v. 1, Novosibirsk, 2013, 122–130 (in Russian)

[6] Demin A. V., Vityaev E. E., “A Method for Building “Natural” Classification”, Information Technology in the Humanities, 15 (2010), 16–22 (in Russian)

[7] Demin A. V., Vityaev E. E., “Financial Time Series: Prediction and Detection of Dynamics Change”, Proc. ZONT conference, 2009, 79–86 (in Russian)

[8] Demin A. V., Vityaev E. E., “A Technology for Predicting Financial Time Series”, Bulletin of 7th Intl. Ershov conference Perspectives of Informatics Systems, 2009, 114–119 (in Russian)

[9] Demin A. V., Vityaev E. E., “Adaptive Control of Multiped Robot”, Procedia Computer Science, 145 (2018), 629–634 | DOI

[10] Demin A. V., Vityaev E. E., “Adaptive Control of Modular Robots”, Biologically Inspired Cognitive Architectures (BICA) for Young Scientists, Advances in Intelligent Systems and Computing, 636, 2018, 204–212 | DOI

[11] Demin A. V., Vityaev E. E., “Learning in a Virtual Model of the C. elegans Nematode for Locomotion and Chemotaxis”, Biologically Inspired Cognitive Architectures, 7 (2014), 9–14 | DOI

[12] Demin A. V., Vityaev E. E., “The Development of a Universal DISCOVERY Knowledge Mining System and its Applications”, Bulletin of Novosibirsk State University: Information Technologies, 7:1 (2009), 73–83 (in Russian)

[13] Demin A. V., Vityaev E. E., Poloz T. L., “The Development of a Universal DISCOVERY Knowledge Mining System and its Applications in Medical Diagnosis”, Proc. ZONT conference, v. 1, Novosibirsk, 2007, 63–70 (in Russian)

[14] Gunopulos D., Khardon R., Mannila H., Saluja S., Toivonen H., and Sharma R. S., “Discovering All Most Specific Sentences”, ACM Transactions on Database Systems, 28:2 (2003) | DOI

[15] Khomicheva I., Demin A. V., Vityaev E. E., “Transcription Factor Binding Site Discovery by the Probabilistic Rules”, Proc. 2nd Workshop on Data mining in Functional Genomics and Proteomics, The 18th European Conference on Machine Learning and the 11th European Conference on Principles and Practice of Knowledge Discovery in Databases (Warsaw, Poland, 2007), 104–109

[16] Kuznetsov S. O., “On the Intractability of Computing the Duquenne-Guigues Base”, J. of Universal Computer Science, 10:8 (2004) | DOI

[17] Vityaev E. E., Kovalerchuk B. K., Fedotov A. M., Barahnin V. B., Belov S. D., Durdin D. S., Demin A. V., “Regularity Discovery and Anomaly Detection in Network Traffic”, Bulletin of Novosibirsk State University: Information Technologies, 6:2 (2008), 57–68 (in Russian)

[18] Vityaev E. E., Demin A. V., Ponomaryov D. K., “Probabilistic Generalization of Formal Concepts”, Programming and Computer Software, 38:5 (2012), 219–230 | DOI

[19] Vityaev E. E., Demin A. V., Ponomaryov D. K., “Probabilistic Concepts in Formal Contexts”, Lecture Notes in Computer Science, 7162, 2012, 394–410 | DOI