<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/neural-structured-learning/blob/v1.4.0/neural_structured_learning/keras/__init__.py) |

Keras APIs for Neural Structured Learning.

## Modules

[`layers`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/keras/layers) module: Keras layers for Neural Structured Learning.

## Classes

[`class AdversarialRegularization`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/keras/AdversarialRegularization): Wrapper thats adds adversarial regularization to a given [`tf.keras.Model`](https://www.tensorflow.org/api_docs/python/tf/keras/Model).

[`class GraphRegularization`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/keras/GraphRegularization): Class that wraps a given `Keras` model to include graph regularization.

## Functions

[`adversarial_loss(...)`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/keras/adversarial_loss): Computes the adversarial loss for `model` given `features` and `labels`.