Architectures · advanced · concept 63 of 176
State Space Models (Mamba)
An alternative to Transformers that processes sequences with linear-time complexity instead of quadratic attention. Mamba and S4 are the foundational SSM architectures, and hybrid attention-SSM designs now appear in production models, offering advantages for very long sequences.
Key terms
Linear complexitySelective SSMS4Long-range dependencies
Learn these first
Videos
▶ What are State Space Models? Redefining AI & Machine Learning with Data ↗
IBM Technology · YouTube
▶ Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Paper Explained) ↗
Yannic Kilcher · YouTube
Guides and articles
Courses, papers, and more