Gu et al: Efficiently Modeling Long Sequences with Structured State Spaces
- papers: https://arxiv.org/pdf/2111.00396.pdf
- Video: Efficiently Modeling Long Sequences with Structured State Spaces
- Open review version: https://openreview.net/pdf?id=uYLFoz1vlAC
- review notes: https://openreview.net/forum?id=uYLFoz1vlAC
- state space continious representation: https://en.wikipedia.org/wiki/State-space_representation
- previous work: https://openreview.net/pdf?id=yWd42CWN3c
- based off of hippo: https://proceedings.neurips.cc/paper/2020/hash/102f0bb6efb3a6128a3c750dd16729be-Abstract.html
- https://papertalk.org/papertalks/9174
- https://github.com/HazyResearch/hippo-code
- https://proceedings.neurips.cc/paper/2020/file/102f0bb6efb3a6128a3c750dd16729be-Paper.pdf
- https://crossminds.ai/video/hippo-recurrent-memory-with-optimal-polynomial-projections-606fddf7f43a7f2f827bf91d/
- https://proceedings.neurips.cc/paper/2020/file/102f0bb6efb3a6128a3c750dd16729be-Paper.pdf
Past Similar Work: Legendre Memory Unit
- https://www.youtube.com/watch?v=8t64QaTdBcU
- https://proceedings.neurips.cc/paper/2019/file/952285b9b7e7a1be5aa7849f32ffff05-Paper.pdf
- https://arxiv.org/abs/2102.11417
- https://en.wikipedia.org/wiki/Legendre_polynomials#Definition_by_construction_as_an_orthogonal_system
State space papers:
- https://www.sciencedirect.com/science/article/pii/S0022000067800096
- https://orb.binghamton.edu/electrical_fac/3/
- http://web.mit.edu/2.14/www/Handouts/StateSpace.pdf
- https://www.lunduniversity.lu.se/lup/publication/ba1ac2a2-373f-45d5-a633-7b36aeace6da
- https://lucris.lub.lu.se/ws/portalfiles/portal/22584321/TEAT_7245.pdf