tf.keras.regularizers.l1_l2

Create a regularizer that applies both L1 and L2 penalties.

Compat aliases for migration

See Migration guide for more details.

tf.keras.regularizers.l1_l2(
    l1=0.01, l2=0.01
)

The L1 regularization penalty is computed as:

ℓ_{1} p e n a l t y = ℓ_{1} \sum_{i = 0}^{n} | x_{i} |

$\ell_1\,\,penalty =\ell_1\sum_{i=0}^n|x_i|$

The L2 regularization penalty is computed as:

ℓ_{2} p e n a l t y = ℓ_{2} \sum_{i = 0}^{n} x_{i}^{2}

$\ell_2\,\,penalty =\ell_2\sum_{i=0}^nx_i^2$

Arguments
`l1`	Float; L1 regularization factor.
`l2`	Float; L2 regularization factor.

Returns
An L1L2 Regularizer with the given regularization factors.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2020-10-01 UTC.

Arguments