Výsledky vyhledávání - "Hagmann, Michael"

Report

Early Prediction of Causes (not Effects) in Healthcare by Long-Term Clinical Time Series Forecasting

Autor: Staniek, Michael, Fracarolli, Marius, Hagmann, Michael, Riezler, Stefan

Machine learning for early syndrome diagnosis aims to solve the intricate task of predicting a ground truth label that most often is the outcome (effect) of a medical consensus definition applied to observed clinical measurements (causes), given clin

Externí odkaz: http://arxiv.org/abs/2408.03816

Zobrazit plný text záznamu

Report

Validity problems in clinical machine learning by indirect data labeling using consensus definitions

Autor: Hagmann, Michael, Schamoni, Shigehiko, Riezler, Stefan

We demonstrate a validity problem of machine learning in the vital application area of disease diagnosis in medicine. It arises when target labels in training data are determined by an indirect measurement, and the fundamental measurements needed to

Externí odkaz: http://arxiv.org/abs/2311.03037

Zobrazit plný text záznamu

Report

Towards Inferential Reproducibility of Machine Learning Research

Autor: Hagmann, Michael, Meier, Philipp, Riezler, Stefan

Reliability of machine learning evaluation -- the consistency of observed evaluation scores across replicated model training runs -- is affected by several sources of nondeterminism which can be regarded as measurement noise. Current tendencies to re

Externí odkaz: http://arxiv.org/abs/2302.04054

Zobrazit plný text záznamu

Report

Ensembling Neural Networks for Improved Prediction and Privacy in Early Diagnosis of Sepsis

Autor: Schamoni, Shigehiko, Hagmann, Michael, Riezler, Stefan

Publikováno v: Proceedings of the 7th Machine Learning for Healthcare Conference, PMLR 182:123-145, 2022

Ensembling neural networks is a long-standing technique for improving the generalization error of neural networks by combining networks with orthogonal properties via a committee decision. We show that this technique is an ideal fit for machine learn

Externí odkaz: http://arxiv.org/abs/2209.00439

Zobrazit plný text záznamu

Report

False perfection in machine prediction: Detecting and assessing circularity problems in machine learning

Autor: Hagmann, Michael, Riezler, Stefan

This paper is an excerpt of an early version of Chapter 2 of the book "Validity, Reliability, and Significance. Empirical Methods for NLP and Data Science", by Stefan Riezler and Michael Hagmann, published in December 2021 by Morgan & Claypool. Pleas

Externí odkaz: http://arxiv.org/abs/2106.12417

Zobrazit plný text záznamu