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/

Zendy Plus

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

Zendy Tools

Zendy Open

In this paper, we investigate whether is it possible to train a neuralnetwork directly from user inputs. We consider this approach to be highlyrelevant for applications in which the point of optimality is not well-definedand user-dependent. Our application is medical image denoising which isessential in fluoroscopy imaging. In this field every user, i.e. physician, hasa different flavor and image quality needs to be tailored towards eachindividual.  To address this important problem, we propose to construct a loss functionderived from a forced-choice experiment. In order to make the learning problemfeasible, we operate in the domain of precision learning, i.e., we inspire thenetwork architecture by traditional signal processing methods in order toreduce the number of trainable parameters. The algorithm that was used for thisis a Laplacian pyramid with only six trainable parameters.  In the experimental results, we demonstrate that two image experts who preferdifferent filter characteristics between sharpness and de-noising can becreated using our approach. Also models trained for a specific user performbest on this users test data. This approach opens the way towardsimplementation of direct user feedback in deep learning and is applicable for awide range of application.

User Loss -- A Forced-Choice-Inspired Approach to Train Neural Networks directly by User Interaction