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

We propose an interactive editing method that allows humans to help deepneural networks (DNNs) learn a latent space more consistent with humanknowledge, thereby improving classification accuracy on indistinguishableambiguous data. Firstly, we visualize high-dimensional data features throughdimensionality reduction methods and design an interactive system\textit{SpaceEditing} to display the visualized data. \textit{SpaceEditing}provides a 2D workspace based on the idea of spatial layout. In this workspace,the user can move the projection data in it according to the system guidance.Then, \textit{SpaceEditing} will find the corresponding high-dimensionalfeatures according to the projection data moved by the user, and feed thehigh-dimensional features back to the network for retraining, thereforeachieving the purpose of interactively modifying the high-dimensional latentspace for the user. Secondly, to more rationally incorporate human knowledgeinto the training process of neural networks, we design a new loss functionthat enables the network to learn user-modified information. Finally, Wedemonstrate how \textit{SpaceEditing} meets user needs through three casestudies while evaluating our proposed new method, and the results confirm theeffectiveness of our method.

SpaceEditing: Integrating Human Knowledge into Deep Neural Networks via Interactive Latent Space Editing