CONVOLUTIONAL STRUCTURED STATE SPACE MODEL
    1.
    发明公开

    公开(公告)号:US20240127041A1

    公开(公告)日:2024-04-18

    申请号:US18452714

    申请日:2023-08-21

    CPC classification number: G06N3/0464 G06F17/16 G06N3/049

    Abstract: Systems and methods are disclosed related to a convolutional structured state space model (ConvSSM), which has a tensor-structured state but a continuous-time parameterization and linear state updates. The linearity may be exploited to use parallel scans for subquadratic parallelization across the spatiotemporal sequence. The ConvSSM effectively models long-range dependencies and, when followed by a nonlinear operation forms a spatiotemporal layer (ConvS5) that does not require compressing frames into tokens, can be efficiently parallelized across the sequence, provides an unbounded context, and enables fast autoregressive generation.

Patent Agency Ranking