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

The terms multi-task learning and multitasking are easily confused.Multi-task learning refers to a paradigm in machine learning in which a networkis trained on various related tasks to facilitate the acquisition of tasks. Incontrast, multitasking is used to indicate, especially in the cognitive scienceliterature, the ability to execute multiple tasks simultaneously. Whilemulti-task learning exploits the discovery of common structure between tasks inthe form of shared representations, multitasking is promoted by separatingrepresentations between tasks to avoid processing interference. Here, we buildon previous work involving shallow networks and simple task settings suggestingthat there is a trade-off between multi-task learning and multitasking,mediated by the use of shared versus separated representations. We show thatthe same tension arises in deep networks and discuss a meta-learning algorithmfor an agent to manage this trade-off in an unfamiliar environment. We displaythrough different experiments that the agent is able to successfully optimizeits training strategy as a function of the environment.

Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks