nn_init_recurrent_uniform: Initialize recurrent weight tensor with small deterministic...
In ggmlR: 'GGML' Tensor Operations for Machine Learning
nn_init_recurrent_uniform R Documentation
Initialize recurrent weight tensor with small deterministic values
Description
Uses a fixed zigzag pattern in [-0.01, 0.01] — no RNG, fully reproducible
across all platforms and independent of the R random seed state.
Usage
nn_init_recurrent_uniform(tensor)
Value
Called for its side effect (fills tensor with deterministic small values); invisibly returns NULL.
ggmlR documentation built on July 14, 2026, 1:08 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
| nn_init_recurrent_uniform | R Documentation |
Initialize recurrent weight tensor with small deterministic values
Description
Uses a fixed zigzag pattern in [-0.01, 0.01] — no RNG, fully reproducible across all platforms and independent of the R random seed state.
Usage
nn_init_recurrent_uniform(tensor)
Value
Called for its side effect (fills tensor with deterministic small values); invisibly returns NULL.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.