layer_sparse_conv_2d

Allows for the specification of semi-structured deep distributional regression models which are fitted in a neural network as
proposed by Ruegamer et al. (2023) <doi:10.18637/jss.v105.i02>.
Predictors can be modeled using structured (penalized) linear effects, structured non-linear effects or using an unstructured deep network model.

David Ruegamer

deepregression

Fitting Deep Distributional Regression

Christopher Marquardt

Laetitia Frost

Florian Pfisterer

Philipp Baumann

Chris Kolb

Lucas Kook

layer_sparse_conv_2d function

<dl><dt>filters</dt>
<dd>number of filters</dd>
<dt>kernel_size</dt>
<dd>size of convolutional filter</dd>
<dt>lam</dt>
<dd>regularization strength</dd>
<dt>depth</dt>
<dd>depth of weight factorization</dd>
<dt>...</dt>
<dd>arguments passed to TensorFlow layer</dd></dl>

Arguments

Sparse 2D Convolutional layer — layer_sparse_conv_2d

<dl>

<dt>filters</dt>
<dd>number of filters</dd>


<dt>kernel_size</dt>
<dd>size of convolutional filter</dd>


<dt>lam</dt>
<dd>regularization strength</dd>


<dt>depth</dt>
<dd>depth of weight factorization</dd>


<dt>...</dt>
<dd>arguments passed to TensorFlow layer</dd>

</dl>

Sparse 2D Convolutional layer

layer_sparse_conv_2d: Sparse 2D Convolutional layer

Description

Usage

Value

Arguments