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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The performance of multi-task learning in Convolutional Neural Networks(CNNs) hinges on the design of feature sharing between tasks within thearchitecture. The number of possible sharing patterns are combinatorial in thedepth of the network and the number of tasks, and thus hand-crafting anarchitecture, purely based on the human intuitions of task relationships can betime-consuming and suboptimal. In this paper, we present a probabilisticapproach to learning task-specific and shared representations in CNNs formulti-task learning. Specifically, we propose "stochastic filter groups''(SFG), a mechanism to assign convolution kernels in each layer to "specialist''or "generalist'' groups, which are specific to or shared across differenttasks, respectively. The SFG modules determine the connectivity between layersand the structures of task-specific and shared representations in the network.We employ variational inference to learn the posterior distribution over thepossible grouping of kernels and network parameters. Experiments demonstratethat the proposed method generalises across multiple tasks and shows improvedperformance over baseline methods.

Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels