Transformer Architecture
The is a model structure introduced by in the 2017 paper "Attention Is All You Need," which revolutionized by replacing and units. It is built upon the mechanism, specifically , which allows the model to process input data sequences in parallel rather than serially, effectively capturing and global context. The architecture typically consists of an and a , utilizing to maintain word order and to stabilize training. This framework serves as the foundation for modern , including the series by , by , and by , and has been adapted for other domains such as via the .
[PREVIEW MODE] Definitions streamed at five depths, references, and related terms are available to signed-in readers — [SIGN IN]
Contextual terminology map
KEEP IN VIEW
Ethics, safety & society
Moving as fast as the field, and easier to overlook
- Explainable AI
- Interpretability
- Model Card
- AI Audit
- Algorithmic Bias
- Disparate Impact
- Digital Divide
- WCAG (Web Content Accessibility Guidelines)
- AI Alignment
- Red Teaming
- EU AI Act
- NIST AI RMF (AI Risk Management Framework)
- Frontier Model
- Deepfake
- Content Credentials
- AI Watermarking
- Job Displacement
- Prompt Injection
- Data Poisoning
- Differential Privacy
- GDPR (General Data Protection Regulation)
- Zero-Day
- End-to-End Encryption
- Data Broker
Infrastructure, markets & the economy
The compute, power and capital behind the boom