The Legendre Memory Unit (LMU) is mathematically derived to orthogonalize its continuous-time history – doing so by solving d coupled ordinary differential equations (ODEs), whose phase space linearly maps onto sliding windows of time via the Legendre polynomials up to degree d-1. It is optimal for compressing temporal information.
See paper for equations (markdown isn't working).
Official github repo: https://github.com/abr/lmuSource: Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks
|🤖 No Components Found||You can add them if they exist; e.g. Mask R-CNN uses RoIAlign|