The conjoining of dynamical systems and deep learning has become a topic...
JAX and PyTorch are two popular Python autodifferentiation frameworks. J...
Neural controlled differential equations (Neural CDEs) are a continuous-...
Neural SDEs combine many of the best qualities of both RNNs and SDEs, an...
Stochastic differential equations (SDEs) are a staple of mathematical
mo...
Neural differential equations may be trained by backpropagating gradient...
Neural Controlled Differential Equations (Neural CDEs) are the
continuou...
The `signature method' refers to a collection of feature extraction
tech...
The shapelet transform is a form of feature extraction for time series, ...
Neural ordinary differential equations are an attractive option for mode...
Signatory is a library for calculating signature and logsignature transf...
The classical Universal Approximation Theorem certifies that the univers...
The signature is an infinite graded sequence of statistics known to
char...