MLP forward pass (Geron Ch 9, morie.fn hmmlpf)
Usage
morie_geron_mlp(X, weights, biases, activations)
Arguments
- X
Input batch.
- weights, biases
Per-layer parameters.
- activations
Per-layer activation names or functions.
Value
List with output, activations, pre_activations, n_parameters, estimate, n, method.
Examples
set.seed(1)
X <- matrix(rnorm(5 * 3), 5, 3)
Ws <- list(matrix(rnorm(3 * 4, 0, 0.3), 3, 4),
matrix(rnorm(4 * 2, 0, 0.3), 4, 2))
bs <- list(rep(0, 4), rep(0, 2))
out <- morie_geron_mlp(X, Ws, bs, list("relu", "softmax"))
dim(as.matrix(out))
#> [1] 8 1
