Description Usage Arguments Value
One of FCNN's design objectives (and main advantages) is the complete separation of teaching (and pruning) algorithms from internal network structure workings. This goal is achieved through fast access to (active) weights vector facilitated by FCNN's ‘compressed’ network representation. The following two functions allow users to efficiently retrieve and set network (active) weights vector.
1 2 3 | mlp_set_weights(net, weights)
mlp_get_weights(net)
|
net |
an object of |
weights |
numeric vector of new active weights' values |
mlp_set_weights
returns network (an object of mlp_net
class) with active weights set to given values.
mlp_set_weights
returns numeric vector of active weights' values.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.