Closed ziatdinovmax closed 8 months ago
Currently, we automatically place priors over weights and biases of a neural network in viDKL, effectively turning it into BNN. It may be a good idea to make this optional and allows for using of a regular NN.
Closed via #78
Currently, we automatically place priors over weights and biases of a neural network in viDKL, effectively turning it into BNN. It may be a good idea to make this optional and allows for using of a regular NN.