PolyNODE: Variable-dimension Neural ODEs on M-polyfolds
arXiv:2602.15128v1 Announce Type: cross Abstract: Neural ordinary differential equations (NODEs) are geometric deep learning models based on dynamical systems and flows generated by vector fields …
Per {\AA}hag, Alexander Friedrich, Fredrik Ohlsson, Viktor Vigren N\"aslund
조회수 53회