Biomedical subjects

Lutz Prechelt

Publications and source records attributed to Lutz Prechelt.

3 recordsLinked to original sources

PubMed2007

On understanding the power of judgement in percutaneous coronary intervention.

AIM: Explain how research can advance the state-of the- practice in percutaneous coronary intervention (PCI). METHODS AND RESULTS: Identifying the success factors of PCI; identifying decision- making performance (power of judgement) as the factor that could be advanced faster than is currently the case; explaining why and how such advancement needs a different research approach than those currently pursued in medical research; presenting initial results of this approach in the form of a set of basic concepts (pivoting around risk) that are useful for describing the decision-making process during a PCI. CONCLUSION: Building a terminology (ontology) of PCI decision-making concepts and then eliciting expert knowledge about the decision-making process itself are promising ways of advancing the teachability of PCI and hence the state-of-the practice.

Angioplasty, Balloon, Coronary↗

PubMed1998

Automatic early stopping using cross validation: quantifying the criteria.

Cross validation can be used to detect when overfitting starts during supervised training of a neural network; training is then stopped before convergence to avoid the overfitting ('early stopping'). The exact criterion used for cross validation based early stopping, however, is chosen in an ad-hoc fashion by most researchers or training is stopped interactively. To aid a more well-founded selection of the stopping criterion, 14 different automatic stopping criteria from three classes were evaluated empirically for their efficiency and effectiveness in 12 different classification and approximation tasks using multi-layer perceptrons with RPROP training. The experiments show that, on average, slower stopping criteria allow for small improvements in generalization (in the order of 4%), but cost about a factor of 4 longer in training time.

Journal Article↗

PubMed1997

Investigation of the CasCor Family of Learning Algorithms.

Six learning algorithms are investigated and compared empirically. All of them are based on variants of the candidate training idea of the Cascade Correlation method. The comparison was performed using 42 different datasets from the PROBEN1 benchmark collection. The results indicate: (1) for these problems it is slightly better not to cascade the hidden units; (2) error minimization candidate training is better than covariance maximization for regression problems but may be a little worse for classification problems; (3) for most learning tasks, considering validation set errors during the selection of the best candidate will not lead to improved networks, but for a few tasks it will. Copyright 1997 Elsevier Science Ltd.

Journal Article↗