Regularization

General • 58 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 19547
1985 9693
2018 7735
1943 7700
2016 786
2018 467
1995 378
2016 327
2019 169
2015 133
2018 130
2018 121
2018 89
2013 78
1986 70
2015 58
2020 57
2000 54
2017 49
2017 49
2014 27
2016 27
2018 26
2018 23
2016 22
2016 20
2022 17
2016 15
2017 14
2020 13
2019 12
2019 10
2021 10
2019 9
2013 7
2017 5
2018 4
2022 4
2018 3
2020 3
2016 3
2021 3
2020 3
2019 3
2016 2
2019 2
2017 2
2023 2
2017 2
2020 1
2021 1
2017 1
2023 1
2021 1
2000 0
2015 0