Diagonal State Spaces are as Effective as Structured State Spaces

对角状态空间和结构化状态空间一样有效.

Resurrecting Recurrent Neural Networks for Long Sequences

复活长序列的循环神经网络.

Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers

通过线性状态空间层结合循环、卷积核连续时间模型.

Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks

勒让德记忆单元：循环神经网络中的连续时间表示.

Efficiently Modeling Long Sequences with Structured State Spaces

通过结构化状态空间高效建模长序列.

HiPPO: Recurrent Memory with Optimal Polynomial Projections

HiPPO：具有最优多项式投影的循环记忆.