English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recomputation algorithms collectively refer to a family of methods that aimsto reduce the memory consumption of the backpropagation by selectivelydiscarding the intermediate results of the forward propagation and recomputingthe discarded results as needed. In this paper, we will propose a novel andefficient recomputation method that can be applied to a wider range of neuralnets than previous methods. We use the language of graph theory to formalizethe general recomputation problem of minimizing the computational overheadunder a fixed memory budget constraint, and provide a dynamic programmingsolution to the problem. Our method can reduce the peak memory consumption onvarious benchmark networks by 36%~81%, which outperforms the reduction achievedby other methods.

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation