Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks

Takuro Kutsuna. Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks. In Ulf Brefeld, Élisa Fromont, Andreas Hotho, Arno J. Knobbe, Marloes H. Maathuis, Céline Robardet, editors, Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part II. Volume 11907 of Lecture Notes in Computer Science, pages 266-282, Springer, 2019. [doi]

@inproceedings{Kutsuna19,
  title = {Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks},
  author = {Takuro Kutsuna},
  year = {2019},
  doi = {10.1007/978-3-030-46147-8_16},
  url = {https://doi.org/10.1007/978-3-030-46147-8_16},
  researchr = {https://researchr.org/publication/Kutsuna19},
  cites = {0},
  citedby = {0},
  pages = {266-282},
  booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019, Proceedings, Part II},
  editor = {Ulf Brefeld and Élisa Fromont and Andreas Hotho and Arno J. Knobbe and Marloes H. Maathuis and Céline Robardet},
  volume = {11907},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  isbn = {978-3-030-46147-8},
}