<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/bijectors/masked_autoregressive.py#L499-L622) |

Build the Masked Autoregressive Density Estimator (Germain et al., 2015). (deprecated)

    tfp.bijectors.masked_autoregressive_default_template(
        hidden_layers,
        shift_only=False,
        activation=tf.nn.relu,
        log_scale_min_clip=-5.0,
        log_scale_max_clip=3.0,
        log_scale_clip_gradient=False,
        name=None,
        *args,
        **kwargs
    )

> [!WARNING]
> **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed after 2020-02-01. Instructions for updating: `masked_autoregressive_default_template` is deprecated; use [`tfp.bijectors.AutoregressiveNetwork`](https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors/AutoregressiveNetwork). Also, please note the section "Variable Tracking" in the documentation for [`tfp.bijectors.MaskedAutoregressiveFlow`](https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors/MaskedAutoregressiveFlow).

This will be wrapped in a make_template to ensure the variables are only
created once. It takes the input and returns the `loc` ('mu' in \[Germain et
al. (2015)\]\[1\]) and `log_scale` ('alpha' in \[Germain et al. (2015)\]\[1\]) from
the MADE network.

> [!WARNING]
> **Warning:** This function uses `masked_dense` to create randomly initialized `tf.Variables`. It is presumed that these will be fit, just as you would any other neural architecture which uses `tf.layers.dense`.

#### About Hidden Layers

Each element of `hidden_layers` should be greater than the `input_depth`
(i.e., `input_depth = tf.shape(input)[-1]` where `input` is the input to the
neural network). This is necessary to ensure the autoregressivity property.

#### About Clipping

This function also optionally clips the `log_scale` (but possibly not its
gradient). This is useful because if `log_scale` is too small/large it might
underflow/overflow making it impossible for the `MaskedAutoregressiveFlow`
bijector to implement a bijection. Additionally, the `log_scale_clip_gradient`
`bool` indicates whether the gradient should also be clipped. The default does
not clip the gradient; this is useful because it still provides gradient
information (for fitting) yet solves the numerical stability problem. I.e.,
`log_scale_clip_gradient = False` means
`grad[exp(clip(x))] = grad[x] exp(clip(x))` rather than the usual
`grad[clip(x)] exp(clip(x))`.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `hidden_layers` | Python `list`-like of non-negative integer, scalars indicating the number of units in each hidden layer. Default: `[512, 512]. </td> </tr><tr> <td>`shift_only`<a id="shift_only"></a> </td> <td> Python`bool`indicating if only the`shift`term shall be computed. Default:`False`. </td> </tr><tr> <td>`activation`<a id="activation"></a> </td> <td> Activation function (callable). Explicitly setting to`None`implies a linear activation. </td> </tr><tr> <td>`log_scale_min_clip`<a id="log_scale_min_clip"></a> </td> <td>`float`-like scalar`Tensor`, or a`Tensor`with the same shape as`log_scale`. The minimum value to clip by. Default: -5. </td> </tr><tr> <td>`log_scale_max_clip`<a id="log_scale_max_clip"></a> </td> <td>`float`-like scalar`Tensor`, or a`Tensor`with the same shape as`log_scale`. The maximum value to clip by. Default: 3. </td> </tr><tr> <td>`log_scale_clip_gradient`<a id="log_scale_clip_gradient"></a> </td> <td> Python`bool`indicating that the gradient of <a href="https://www.tensorflow.org/api_docs/python/tf/clip_by_value"><code>tf.clip_by_value</code></a> should be preserved. Default:`False`. </td> </tr><tr> <td>`name`<a id="name"></a> </td> <td> A name for ops managed by this function. Default: 'masked_autoregressive_default_template'. </td> </tr><tr> <td>`*args`<a id="*args"></a> </td> <td>`tf.layers.dense`arguments. </td> </tr><tr> <td>`* \*kwargs`<a id="**kwargs"></a> </td> <td>`tf.layers.dense\` keyword arguments. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| `shift` | `Float`-like `Tensor` of shift terms (the 'mu' in \[Germain et al. (2015)\]\[1\]). |
| `log_scale` | `Float`-like `Tensor` of log(scale) terms (the 'alpha' in \[Germain et al. (2015)\]\[1\]). |

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `NotImplementedError` | if rightmost dimension of `inputs` is unknown prior to graph execution. |

<br />

#### References

\[1\]: Mathieu Germain, Karol Gregor, Iain Murray, and Hugo Larochelle. MADE:
Masked Autoencoder for Distribution Estimation. In *International
Conference on Machine Learning* , 2015. <https://arxiv.org/abs/1502.03509>