DeepAI AI Chat
Log In Sign Up

Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU

by   Patrick Kidger, et al.
University of Oxford

Signatory is a library for calculating signature and logsignature transforms and related functionality. The focus is on making this functionality available for use in machine learning, and as such includes features such as GPU support and backpropagation. To our knowledge it is the first publically available GPU-capable library for these operations. It also implements several new algorithmic improvements, and provides several new features not available in previous libraries. The library operates as a Python wrapper around C++, and is compatible with the PyTorch ecosystem. It may be installed directly via pip. Source code, documentation, examples, benchmarks and tests may be found at <>. The license is Apache-2.0.


page 1

page 2

page 3

page 4


Deepchecks: A Library for Testing and Validating Machine Learning Models and Data

This paper presents Deepchecks, a Python library for comprehensively val...

Differentiable and Learnable Robot Models

Building differentiable simulations of physical processes has recently r...

Differentiable Forward Kinematics for TensorFlow 2

Robotic systems are often complex and depend on the integration of a lar...

Pulse shape discrimination based on the Tempotron: a powerful classifier on GPU

This study introduces the Tempotron, a powerful classifier based on a th...

JAXFit: Trust Region Method for Nonlinear Least-Squares Curve Fitting on the GPU

We implement a trust region method on the GPU for nonlinear least square...

pyGSL: A Graph Structure Learning Toolkit

We introduce pyGSL, a Python library that provides efficient implementat...

MoebInv: C++ libraries for manipulations in non-Euclidean geometry

The introduced package MoebInv contains two CPP libraries for symbolic, ...

Code Repositories


Differentiable computations of the signature and logsignature transforms, on both CPU and GPU. (ICLR 2021)

view repo