A Simple and Efficient Tensor Calculus for Machine Learning

DOI10.3233/FI-2020-1984zbMath1497.68429arXiv2010.03313OpenAlexW3115388305MaRDI QIDQ4988921

Joachim Giesen, Sören Laue, Matthias Mitterreiter

Publication date: 20 May 2021

Published in: Fundamenta Informaticae (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2010.03313

zbMATH Keywords

tensor calculusalgorithmic differentiationmatrix calculustensor notation

Mathematics Subject Classification ID

Symbolic computation and algebraic computation (68W30) Learning and adaptive systems in artificial intelligence (68T05) Multilinear algebra, tensor calculus (15A69)

Related Items (2)

What is the gradient of a scalar function of a symmetric matrix? ⋮ Unnamed Item

Uses Software

• ADOL-C
• ADIC
• Theano
• TAPENADE
• TensorFlow
• DiffSharp
• PyTorch
• Autograd
• JAX
• MatrixCalculus

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the implementation of automatic differentiation tools
• Optimal accumulation of Jacobian matrices by elimination methods on the dual computational graph
• Support-vector networks
• Optimal Jacobian accumulation is NP-complete
• Efficient Computation of Sparse Hessians Using Coloring and Automatic Differentiation
• The Tapenade automatic differentiation tool
• Evaluating Derivatives
• 10.1162/jmlr.2003.3.4-5.993
• Learning representations by back-propagating errors
• A Fast Learning Algorithm for Deep Belief Nets

This page was built for publication: A Simple and Efficient Tensor Calculus for Machine Learning