Regularization

General • 62 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 23567
1985 12164
2018 9275
1943 9231
2016 941
2018 501
1995 413
2016 393
2019 178
2015 137
2018 132
2018 122
2018 103
2013 82
1986 75
2020 66
2015 63
2000 61
2017 52
2017 52
2018 29
2016 29
2014 28
2016 26
2018 25
2016 22
2022 19
2019 16
2016 15
2017 14
2020 13
2019 12
2021 10
2019 9
2013 7
2016 6
2020 5
2017 5
2022 4
2018 4
2021 4
2019 4
2022 4
2020 3
2016 3
2018 3
2020 3
2017 2
2017 2
2019 2
2023 2
2024 2
2020 1
2021 1
2023 1
2017 1
2023 1
2021 1
2000 0
2015 0