Module functional 

Functional interface for neural network operations.

This module provides stateless functions that mirror the module-based activations and operations. Use these when you don’t need a module wrapper (e.g., in custom forward passes).

Example

use aprender::nn::F;
use aprender::autograd::Tensor;

let x = Tensor::randn(&[32, 10]);
let y = F::relu(&x);
let probs = F::softmax(&y, -1);

Functions

dropout

Dropout (must be called with training flag)

gelu

GELU activation (Gaussian Error Linear Unit)

leaky_relu

Leaky ReLU activation: max(negative_slope * x, x)

linear

Linear transformation: y = x @ weight^T + bias

log_softmax

Log softmax along a dimension

relu

ReLU activation: max(0, x)

sigmoid

Sigmoid activation: 1 / (1 + exp(-x))

softmax

Softmax along a dimension

tanh

Tanh activation