RelationModuleType

Enums · AiDotNet.Enums

Types of relation module architectures for Relation Networks.

For Beginners

This determines HOW the network compares two examples. Instead of using a fixed formula (like Euclidean distance), Relation Networks learn a neural network to measure “how related” two examples are. This enum controls the architecture of that comparison network.

How It Works

The relation module learns to compare feature embeddings and output a similarity score. Different architectures provide different ways of computing this learned similarity.

Fields

Field Summary
RelationModuleType Attention Uses attention mechanism to relate features.
RelationModuleType Concatenate Concatenates features and passes through MLP.
RelationModuleType Convolution Stacks features and applies 2D convolution.
RelationModuleType Transformer Uses transformer-style self-attention.
int value__