Regularization

General • 46 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 6596
1943 2903
2018 2670
1985 2251
2016 222
1995 161
2018 131
2015 96
2013 66
2018 53
2019 50
2018 49
2015 49
2017 43
2017 43
1986 41
2016 40
2000 31
2018 31
2014 21
2020 20
2016 17
2016 14
2018 12
2016 12
2018 10
2016 9
2017 8
2017 5
2019 5
2013 4
2018 3
2019 3
2018 3
2016 3
2019 2
2021 2
2019 2
2017 2
2016 1
2017 1
2019 1
2021 1
2017 1
2015 0