assign_within_layer_pos

Takes care of the three possible cases. Both layers have even
number of neurons, both layers have odd numbers, or one of each.

internal

Latent binary Bayesian neural networks (LBBNNs) are implemented using
'torch', an R interface to the LibTorch backend. Supports mean-field variational
inference as well as flexible variational posteriors using normalizing flows.
The standard LBBNN implementation follows Hubin and Storvik (2024) <doi:10.3390/math12060788>,
using the local reparametrization trick as in Skaaret-Lund et al. (2024)
<https://openreview.net/pdf?id=d6kqUKzG3V>. Input-skip connections are also supported,
as described in Høyheim et al. (2025) <doi:10.48550/arXiv.2503.10496>.

Lars Skaaret-Lund

LBBNN

Latent Binary Bayesian Neural Networks Using 'torch'

Aliaksandr Hubin

Eirik Høyheim

assign_within_layer_pos function

<dl><dt>N</dt>
<dd>integer, number of neurons in the first layer.</dd>
<dt>N_u</dt>
<dd>integer, number of neurons in the second layer.</dd>
<dt>input_positions</dt>
<dd>Positions of the neurons in the input layer.</dd>
<dt>neuron_spacing</dt>
<dd>How much space between the neurons.</dd></dl>

Arguments

Function for plotting nodes in the network between two layers. — assign_within_layer_pos

<dl>

<dt>N</dt>
<dd>integer, number of neurons in the first layer.</dd>


<dt>N_u</dt>
<dd>integer, number of neurons in the second layer.</dd>


<dt>input_positions</dt>
<dd>Positions of the neurons in the input layer.</dd>


<dt>neuron_spacing</dt>
<dd>How much space between the neurons.</dd>

</dl>

assign_within_layer_pos: Function for plotting nodes in the network between two layers.

Description

Usage

Value

Arguments