AutoMAT: Automated machine learning: Modelling, Auditing and Testings

What We Do

Tuning of model hyperparameters, features transformation and features selection are activities that can be automated.

Can and should in order to create more time for creative work of data scientists.

Our group develop new algorithms and tools for AutoML (automated model building), AutoEDA (automated exploratory data analysis) and AutoVAT (automated validation, auditing and testing).

Grants

,,MLGenSig: Machine Learning Methods for building the Integrated Genetic Signatures''

NCN 2017-2020

,,DALEX: Descriptive mAchine Learning EXplanations''

NCN 2018-2021

Intsvy: An R package for analyzing international large-scale assessment data

Daniel Caro, Przemysław Biecek (2017)

Journal of Statistical Software https://www.jstatsoft.org/article/view/v081i07

Comprehensive graphical presentation of data from incurred sample reanalysis

Rudzki P, Biecek P, Kaza M (2017)

Bioanalysis https://www.ncbi.nlm.nih.gov/pubmed/28627276

archivist: An R Package for Managing, Recording and Restoring Data Analysis Results

Marcin Kosiński, Przemysław Biecek (2017)

Journal of Statistical Software https://www.jstatsoft.org/article/view/v082i11

Publications

Key works

Recent contributions

Kamil Romaszko, Magda Tatarynowicz, Mateusz Urbański, Przemysław Biecek (2019), modelDown: automated website generator with interpretable documentation for predictive machine learning models, Journal of Open Source Software https://www.theoj.org/joss-papers/joss.01444/10.21105.joss.01444.pdf
Alicja Gosiewska, Przemyslaw Biecek (2019), SAFE ML: Surrogate Assisted Feature Extraction for Model Learning, ARXIV: arXiv:1902.11035v1 https://arxiv.org/abs/1902.11035