Uses of Class
io.github.kirstenali.deepj.nn.Module

Packages that use Module

Package	Description
io.github.kirstenali.deepj.nn	Neural networks composed from DeepJ tensors, layers, autograd and backend operations.

Uses of Module in io.github.kirstenali.deepj.nn

Subclasses of Module in io.github.kirstenali.deepj.nn

Modifier and Type	Class	Description
final class	Activation	Adapts DeepJ activations to the existing Layer contract.
final class	Autoencoder	Composable encoder/decoder, sharing the same parameter and autograd system as every DeepJ layer.
final class	BatchNorm	Channel-axis (axis 1) normalization, using backend reductions and persistent FLOAT32 running statistics.
final class	Conv1D	Temporal cross-correlation for [batch, channels, length], sharing the 2D implementation.
final class	Conv2D	Cross-correlation of [batch, channels, height, width] inputs, using gather and matrix multiplication.
final class	Dropout	Inverted dropout.
final class	EncoderAttention	Bidirectional multi-head attention with optional padding masks and backend-resident softmax.
final class	Flatten	Flattens an inclusive axis range; defaults to preserving the first (batch) axis.
final class	GlobalAveragePool	Averages every spatial axis of [batch, channels, ...], returning [batch, channels].
final class	GRU	Batch-first GRU layer; compose layers with Sequential for stacked recurrence.
final class	GRUCell	Reset-after GRU, with reset/update/candidate gate order and separate projection biases.
final class	LSTM	Batch-first LSTM layer; compose layers with Sequential for stacked recurrence.
final class	LSTMCell	LSTM with input/forget/candidate/output gate order and explicit cell memory.
final class	Pool1D	Max/average pooling of [batch, channels, length] inputs.
final class	Pool2D	Floor-mode max/average pooling of channel-first images.
class	Recurrent	Batch-first recurrent sequence execution, with optional lengths and caller-owned initial/final state.
class	RecurrentCell	Shared input/state validation and DeepJ linear projections for recurrent cells.
final class	Reshape	Reshapes the full tensor, with at most one inferred (-1) dimension.
final class	RNN	Batch-first RNN layer; compose layers with Sequential for stacked recurrence.
final class	RNNCell	Elman recurrent cell with tanh activation.
final class	Sequential	Ordered composition of existing or new DeepJ layers.
final class	TransformerEncoder	Stacked encoder for [batch, time, width] embeddings, with padding masks and masked mean pooling.
final class	TransformerEncoderLayer	Pre-normalized, bidirectional encoder block reusing DeepJ linear layers and LayerNorm.