tf.keras.regularizers.l1

TensorFlow 1 version View source on GitHub

Create a regularizer that applies an L1 regularization penalty.

The L1 regularization penalty is computed as:

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

l Float; L1 regularization factor.

An L1 Regularizer with the given regularization factor.