Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology

Autor: Stefan Studer, Thanh Binh Bui, Christian Drescher, Alexander Hanuschkin, Ludwig Winkler, Steven Peters, Klaus-Robert Müller

Publikováno v: Machine Learning and Knowledge Extraction, Vol 3, Iss 2, Pp 392-413 (2021)

Machine learning is an established and frequently used technique in industry and academia, but a standard process model to improve success and efficiency of machine learning applications is still missing. Project organizations and machine learning pr

Externí odkaz: https://doaj.org/article/ba462d1efae54b0eadc2a3d869adfe8a

Stochastic Control for Bayesian Neural Network Training

Autor: Ludwig Winkler, César Ojeda, Manfred Opper

Publikováno v: Entropy, Vol 24, Iss 8, p 1097 (2022)

In this paper, we propose to leverage the Bayesian uncertainty information encoded in parameter distributions to inform the learning procedure for Bayesian models. We derive a first principle stochastic differential equation for the training dynamics

Externí odkaz: https://doaj.org/article/7d7273ff5d5b4a14902a25c51007f2d9

High-fidelity molecular dynamics trajectory reconstruction with bi-directional neural networks

Autor: Ludwig Winkler, Klaus-Robert Müller, Huziel E Sauceda

Molecular dynamics (MD) simulations are a cornerstone in science, enabling the investigation of a system’s thermodynamics all the way to analyzing intricate molecular interactions. In general, creating extended molecular trajectories can be a compu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b806987419ef9825130272eadef9d594
https://depositonce.tu-berlin.de/handle/11303/17070

Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology

Autor: Alexander Hanuschkin, Stefan Studer, Ludwig Winkler, Christian Drescher, Thanh Binh Bui, Steven Peters, Klaus-Robert Müller

Publikováno v: Machine Learning and Knowledge Extraction
Volume 3
Issue 2
Pages 392-413
Machine Learning and Knowledge Extraction, Vol 3, Iss 392, Pp 392-413 (2021)

Machine learning is an established and frequently used technique in industry and academia but a standard process model to improve success and efficiency of machine learning applications is still missing. Project organizations and machine learning pra

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::086bf6e5f6ceb4dcbe1db675119e306b

Unobtrusive heart rate estimation during physical exercise using photoplethysmographic and acceleration data

Autor: Larissa Laich, Benedikt Lorch, Ludwig Winkler, Bjoern M. Eskofier, Lea Schroeder, Patrick Mullan, Cristian Pasluosta, Heike Leutheuser, Christoph Luckner, Christoph M. Kanzler, Robert Richer, Frederik Riedel

Publikováno v: EMBC

Photoplethysmography (PPG) is a non-invasive, inexpensive and unobtrusive method to achieve heart rate monitoring during physical exercises. Motion artifacts during exercise challenge the heart rate estimation from wrist-type PPG signals. This paper

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0007eb44ebf18bae4e5d124f5c911c3a
https://doi.org/10.1109/embc.2015.7319787