Adjoint computation and Backpropagation - Archive ouverte HAL Access content directly
Conference Papers Year :

Adjoint computation and Backpropagation

(1)
1

Abstract

In this talk Dr Pallez will discuss the impact of memory in the computation of automatic differentiation or for the backpropagation step of machine learning algorithms. He will show different strategies based on the amount of memory available. In particular he will discuss optimal strategies when one can reuse memory slots, and when considering a hierarchical memory platform
Fichier principal
Vignette du fichier
aupy_royal_society.pdf (3.8 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02400746 , version 1 (09-12-2019)

Identifiers

  • HAL Id : hal-02400746 , version 1

Cite

Guillaume Pallez. Adjoint computation and Backpropagation. Meeting of the Royal Society -- Numerical algorithms for high-performance computational science, Apr 2019, London, United Kingdom. ⟨hal-02400746⟩
25 View
36 Download

Share

Gmail Facebook Twitter LinkedIn More