AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Deep Signature Transforms

Patrick Kidger, Patric Bonnier, Imanol Perez Arribas, Cristopher Salvi, Terry Lyons

NeurIPS 2019 · Architectures and efficiency › CNN design · approach: Invertible and wide-network analysis · 50 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a learned transformation before the signature instead of a fixed signature feature transformDeepSigNet vs Neural-Sig · Fractional Brownian motion Hurst estimation test setMSE: 1.1 \times 10^{-2} -> 2.1 \times 10^{-4}Improved
Use three smaller Neural-Lift-Signature blocks instead of one large blockDeeperSigNet vs DeepSigNet · Fractional Brownian motion Hurst estimation test setMSE: 2.1 \times 10^{-4} -> 1.6 \times 10^{-4}Improved
Use deep signature memory instead of a comparable recurrent networkDeep signature RL model vs RNN · Partially observed Mountain Carepisodes to consistently solveImproved
Train the generator using the signature-kernel MMD objectiveDeep signature generative model · Ornstein–Uhlenbeck process generationMMD loss: 6.6 \times 10^{-4}Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy