Atlas · GenAI 2026
State Space Models
State-Space Models (SSM / Mamba)
conceptPeak: 2024Neural ArchitecturesAI consensus: 1/3
Prerequisites
- hardDeep Learning
SSMs are an alternative to attention with recurrent state updates — understanding what they replace requires DL fundamentals
- hardLinear Algebra
State-space equations are linear dynamical systems: x' = Ax + Bu — pure linear algebra
Recommended reference
Gu & Dao (2023) 'Mamba: Linear-Time Sequence Modeling with Selective State Spaces' — arXiv:2312.00752; the foundational paper
Notes from AI deep research
Anthropic Opus
Mamba = alternatywa attention z liniowa zlozonoscia. Post-Transformer worth watching
Google Deep Think
Post-transformerowe; nieskończone okna kontekstowe [G#24]
Related skills
- → is subcategory of: Deep Learning(3/3)