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

Modern deep neural network (DNN) systems are highly configurable with large anumber of options that significantly affect their non-functional behavior, forexample inference time and energy consumption. Performance models allow tounderstand and predict the effects of such configuration options on systembehavior, but are costly to build because of large configuration spaces.Performance models from one environment cannot be transferred directly toanother; usually models are rebuilt from scratch for different environments,for example different hardware. Recently, transfer learning methods have beenapplied to reuse knowledge from performance models trained in one environmentin another. In this paper, we perform an empirical study to understand theeffectiveness of different transfer learning strategies for buildingperformance models of DNN systems. Our results show that transferringinformation on the most influential configuration options and theirinteractions is an effective way of reducing the cost to build performancemodels in new environments.

Transfer Learning for Performance Modeling of Deep Neural Network Systems