Regularization

General • 43 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.

Method Year Papers
2014 5775
1943 2493
2018 2252
1985 1934
2016 203
1995 150
2018 106
2015 88
2013 62
2018 48
2018 47
2015 45
2017 40
2017 40
2019 38
1986 38
2018 30
2016 21
2014 21
2016 16
2020 16
2016 14
2016 12
2018 11
2018 10
2016 8
2017 7
2017 5
2019 4
2018 3
2016 3
2013 3
2017 2
2019 2
2019 2
2019 2
2016 1
2017 1
2021 1
2019 1
2017 1
2015 0