kaira.models.components.MLPEncoder

Inheritance diagram of MLPEncoder

Inheritance diagram for MLPEncoder

class kaira.models.components.MLPEncoder(in_features: int, out_features: int, hidden_dims: List[int] | None = None, activation: Module | None = None, output_activation: Module | None = None, *args: Any, **kwargs: Any)[source]

Bases: BaseModel

Multi-Layer Perceptron (MLP) Encoder for communication systems.

This module implements a simple MLP-based encoder that maps input messages to encoded signals suitable for transmission over a communication channel.

Methods

__init__

Initialize the MLPEncoder.

forward

Forward pass of the MLPEncoder.

Examples using kaira.models.components.MLPEncoder

Multiple Access Channel Model for Joint Encoding

Multiple Access Channel Model for Joint Encoding

Sequential Model for Modular Neural Network Design

Sequential Model for Modular Neural Network Design
__init__(in_features: int, out_features: int, hidden_dims: List[int] | None = None, activation: Module | None = None, output_activation: Module | None = None, *args: Any, **kwargs: Any)[source]

Initialize the MLPEncoder.

Parameters:

  • in_features (int) – The dimensionality of the input messages.

  • out_features (int) – The dimensionality of the output encoded signals.

  • hidden_dims (List[int], optional) – Dimensions of hidden layers. If None, a single hidden layer with (in_features + out_features) // 2 units is used.

  • activation (nn.Module, optional) – Activation function to use between layers. If None, ReLU is used.

  • output_activation (nn.Module, optional) – Activation function to use at the output. If None, no activation is applied to the output.

  • *args – Variable positional arguments passed to the base class.

  • **kwargs – Variable keyword arguments passed to the base class.

forward(x: Tensor, *args: Any, **kwargs: Any) → Tensor[source]

Forward pass of the MLPEncoder.

Parameters:

  • x (torch.Tensor) – Input tensor of shape (batch_size, in_features).

  • *args – Additional positional arguments (unused).

  • **kwargs – Additional keyword arguments (unused).

Returns:

Output tensor of shape (batch_size, out_features).

Return type:

torch.Tensor