Sign inSign in
ConceptAI & ML

State space models

A class of models including Mamba that are taking off as alternatives to transformers.
as Nathan Lambert defines itStanford UniversityThe wording closest to all 5 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

4

Each in their own terms, from the easiest level.

  • Sergey Levine

    UC Berkeley · Undergraduate

    Models that represent a system's dynamics using latent states alongside observation and reward models.
    • 20:44RL with Sequence Models & Language Models, Part 1 (CS 285, Lecture 21)
    • 2:27Exploration of advanced topics in deep reinforcement learning
  • Steven Feng

    Stanford University · Undergraduate

    Models that sequence using continuous state updates and maintain a compressed internal state over time.
    • 1:15:57Overview of Transformers (Stanford CS25: Transformers United V6)
  • Irina Rish

    Université de Montréal, MILA · Research

    Alternative models like Mamba that provide better treatment of very long-range dependencies more efficiently than attention.
    • 1:02:22Emergent Behaviors in Foundational Models

Lectures that assume it

13

The first 12 are shown.

Connections

28

The lectures that define it or assume it, and the concepts next to it.

4 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.