7 citations · 7 across the 1 of their papers we have counts for
3 papers
stat.ML2021★ 7 cited
Framing RNN as a kernel method: A neural ODE approach
Adeline Fermanian, Pierre Marion, Jean-Philippe Vert +1
Building on the interpretation of a recurrent neural network (RNN) as a continuous-time neural differential equation, we show, under appropriate conditions, that the solution of a…
cs.LG2020
A Generalised Signature Method for Multivariate Time Series Feature Extraction
James Morrill, Adeline Fermanian, Patrick Kidger +1
The 'signature method' refers to a collection of feature extraction techniques for multivariate time series, derived from the theory of controlled differential equations. There is…
stat.ML2019
Embedding and learning with signatures
Adeline Fermanian
Sequential and temporal data arise in many fields of research, such as quantitative finance, medicine, or computer vision. A novel approach for sequential learning, called the sign…