AI Glossary
The complete dictionary of Artificial Intelligence
162
categories
2,032
subcategories
23,060
terms
terms
Add & Norm Layer
Residual normalization layer applied after the attention mechanism, combining the attention output with the original input (residual connection) before normalizing the sum.
terms
Linear Projection in Attention
Linear transformation (multiplication by a weight matrix) applied to input embeddings to generate Query, Key, and Value vectors, allowing the model to learn attention-specific representation spaces.
🔍