|---| | [ View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/util.py#L202-L224) | Creates multivariate standard `Normal` distribution. #### View aliases **Main aliases** [`tfp.layers.util.default_multivariate_normal_fn`](https://www.tensorflow.org/probability/api_docs/python/tfp/layers/default_multivariate_normal_fn)
tfp.layers.default_multivariate_normal_fn( dtype, shape, name, trainable, add_variable_fn )


| ## Args || |---|---| | `dtype` | Type of parameter's event. | | `shape` | Python `list`-like representing the parameter's event shape. | | `name` | Python `str` name prepended to any created (or existing) [`tf.Variable`](https://www.tensorflow.org/api_docs/python/tf/Variable)s. | | `trainable` | Python `bool` indicating all created [`tf.Variable`](https://www.tensorflow.org/api_docs/python/tf/Variable)s should be added to the graph collection `GraphKeys.TRAINABLE_VARIABLES`. | | `add_variable_fn` | `tf.get_variable`-like `callable` used to create (or access existing) [`tf.Variable`](https://www.tensorflow.org/api_docs/python/tf/Variable)s. |



| ## Returns || |---|---| | Multivariate standard `Normal` distribution. ||