Αρχιτεκτονική

Embedding Layer

Ορισμός

The initial layer of a neural network that maps discrete tokens (words, image patches) to dense continuous vectors that the model can process. The quality of an embedding layer significantly affects downstream task performance.

Σχετικοί Όροι

Embedding

A numerical representation of data (text, images, etc.) in a high-dimensional vector space where semantically similar items are mathematically close together. Embeddings are the foundational building block for semantic search, RAG pipelines, and recommendation systems.

Tokenization

The process of splitting raw text into smaller units called tokens—typically sub-words or word-pieces—that serve as the basic input unit for language models. Token count determines both model context limits and API pricing, making tokenization an important operational consideration.

Transformer

The dominant neural network architecture for language, vision, and multimodal AI, introduced in the 2017 "Attention Is All You Need" paper. Transformers use self-attention to process all tokens in parallel, enabling training on internet-scale data and powering every major LLM in use today.

Χρειάζεστε Βοήθεια για να Κατανοήσετε το AI;

Κλείστε μια συμβουλευτική για να συζητήσετε πώς οι έννοιες AI εφαρμόζονται στις προκλήσεις σας.