@article{2692,
  author = {Erik Dovgan, Jaka Sodnik, Bogdan Filipic},
  title = {Optimization of End-to-End Deep Learning for Obtaining Human-Like Driving Models},
  journal = {Transactions on Machine Design},
  year = {2019},
  volume = {7},
  number = {1},
  doi = {},
  url = {http://www.dline.info/tmd/fulltext/v7n1/tmdv7n1_1.pdf},
  abstract = {Modeling human driving with human-like driving models can help companies in the evaluation of human
drivers. While a human-like driving model can be tested in various scenarios, this is not feasible for driver evaluation due to time constraints. During the evaluation, only a small set of driving data can be typically collected for each driver, which represents an issue for advanced modeling approaches such as deep learning. To overcome this issue, an optimization approach is proposed, which tunes deep learning when a small learning dataset is available.},
}