TY - GEN 
AU - Egele R
AU - Mohr F
AU - Viering T
AU - Balaprakash P.
PY - 2024
SN - 9252312
UR - http://hdl.handle.net/10818/61892
AB - To reach high performance with deep learning, hyperparameter optimization (HPO) is essential. This process is usually time-consuming due to costly evaluations of neural networks. Early discarding techniques limit the resources granted to unpromising...
LA - eng
PB - Neurocomputing
KW - Deep neural network
KW - Hyperparameter optimization
KW - Learning curve
KW - Multi-fidelity optimization
TI - The unreasonable effectiveness of early discarding after one epoch in neural network hyperparameter optimization
DO - 10.1016/j.neucom.2024.127964
ER -