Primitives

Primitives are the fundamental building blocks of NeuroScript. They wrap PyTorch operations and provide the foundation for building complex neural architectures.

Categories

Layers

• Linear - Fully-connected transformation
• Conv2d - 2D convolutional layer
• Embedding - Token embedding

Activations

• ReLU - Rectified Linear Unit
• GELU - Gaussian Error Linear Unit

Normalization

• LayerNorm - Layer normalization
• BatchNorm - Batch normalization

Regularization

• Dropout - Dropout regularization

Structural

• Flatten - Dimension flattening
• Concat - Tensor concatenation

Usage

All primitives are automatically available in your NeuroScript programs. Simply use them by name:

neuron MyModel:
    graph:
        in -> Linear(512, 256) -> GELU() -> out

Shape Contracts

Every primitive has a well-defined shape contract that specifies:

• Input shapes (what tensor dimensions are expected)
• Output shapes (what dimensions are produced)
• Parameter constraints (what values are valid)

The NeuroScript compiler validates all shape contracts at compile time, catching dimensional errors before code generation.