Regularization

General • 54 methods

Regularization strategies are designed to reduce the test error of a machine learning algorithm, possibly at the expense of training error. Many different forms of regularization exist in the field of deep learning. Below you can find a constantly updating list of regularization strategies.

Subcategories

Method Year Papers
2014 10705
1943 4518
2018 4358
1985 4256
2016 314
2018 272
1995 226
2016 147
2015 117
2019 112
2018 86
2013 73
2018 72
2015 54
2018 51
1986 50
2017 47
2017 47
2000 38
2020 33
2014 25
2016 22
2018 18
2018 16
2016 15
2016 15
2016 15
2017 11
2020 9
2021 9
2019 8
2019 8
2019 7
2017 5
2013 5
2018 4
2018 3
2016 3
2021 3
2020 3
2019 2
2017 2
2019 2
2017 2
2020 2
2020 1
2021 1
2017 1
2016 1
2022 1
2021 1
2015 0