Struct LSTM 

pub struct LSTM { /* private fields */ }

Long Short-Term Memory (LSTM) layer.

Standard LSTM with forget, input, output gates and cell state.

f_t = σ(W_if @ x_t + W_hf @ h_{t-1} + b_f)  // forget gate
i_t = σ(W_ii @ x_t + W_hi @ h_{t-1} + b_i)  // input gate
g_t = tanh(W_ig @ x_t + W_hg @ h_{t-1} + b_g)  // candidate cell
o_t = σ(W_io @ x_t + W_ho @ h_{t-1} + b_o)  // output gate
c_t = f_t * c_{t-1} + i_t * g_t  // cell state
h_t = o_t * tanh(c_t)  // hidden state

Reference

Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation.

Implementations

impl LSTM

pub fn new(input_size: usize, hidden_size: usize) -> Self

pub fn forward_step( &self, x: &Tensor, h: &Tensor, c: &Tensor, ) -> (Tensor, Tensor)

Forward pass for single timestep.

pub fn forward_sequence( &self, x: &Tensor, h0: Option<&Tensor>, c0: Option<&Tensor>, ) -> (Tensor, Tensor, Tensor)

Forward pass for sequence [batch, seq_len, input_size].

pub fn input_size(&self) -> usize

pub fn hidden_size(&self) -> usize

Trait Implementations

impl Debug for LSTM

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Module for LSTM

fn forward(&self, input: &Tensor) -> Tensor

Perform forward computation.

fn parameters(&self) -> Vec<&Tensor>

Get references to all learnable parameters.

fn parameters_mut(&mut self) -> Vec<&mut Tensor>

Get mutable references to all learnable parameters.

fn train(&mut self)

Set the module to training mode.

fn eval(&mut self)

Set the module to evaluation mode.

fn training(&self) -> bool

Check if the module is in training mode.

fn refresh_caches(&mut self)

Refresh any cached computations after parameters have been modified.

fn zero_grad(&mut self)

Zero out gradients for all parameters.

fn num_parameters(&self) -> usize

Get the number of learnable parameters.