#include <jumprelu_sparse_autoencoder.hpp>
|
| float | l0_coefficient = 1e-3f |
| | λ, the L0 penalty's weight: the loss is mean((x̂ - x)²) + λ * L0, L0 averaged over the batch. The paper sums the squared error over dimensions; with the mean, λ is smaller by the input dimension.
|
| |
| float | bandwidth = 1e-3f |
| | ε, the bandwidth of the rectangle kernel that stands in for the step's derivative.
|
| |
| float | initial_threshold = 1e-3f |
| | Every latent's starting threshold θ (the paper's 0.001).
|
| |
| uint64_t | seed = 0 |
| |
◆ bandwidth
| float pulsatrix::JumpReLUSaeOptions::bandwidth = 1e-3f |
ε, the bandwidth of the rectangle kernel that stands in for the step's derivative.
◆ initial_threshold
| float pulsatrix::JumpReLUSaeOptions::initial_threshold = 1e-3f |
Every latent's starting threshold θ (the paper's 0.001).
◆ l0_coefficient
| float pulsatrix::JumpReLUSaeOptions::l0_coefficient = 1e-3f |
λ, the L0 penalty's weight: the loss is mean((x̂ - x)²) + λ * L0, L0 averaged over the batch. The paper sums the squared error over dimensions; with the mean, λ is smaller by the input dimension.
◆ seed
| uint64_t pulsatrix::JumpReLUSaeOptions::seed = 0 |
The documentation for this struct was generated from the following file: