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

With the dramatic advances in deep learning technology, machine learningresearch is focusing on improving the interpretability of model predictions aswell as prediction performance in both basic and applied research. While deeplearning models have much higher prediction performance than traditionalmachine learning models, the specific prediction process is still difficult tointerpret and/or explain. This is known as the black-boxing of machine learningmodels and is recognized as a particularly important problem in a wide range ofresearch fields, including manufacturing, commerce, robotics, and otherindustries where the use of such technology has become commonplace, as well asthe medical field, where mistakes are not tolerated. This bulletin is based onthe summary of the author's dissertation. The research summarized in thedissertation focuses on the attention mechanism, which has been the focus ofmuch attention in recent years, and discusses its potential for both basicresearch in terms of improving prediction performance and interpretability, andapplied research in terms of evaluating it for real-world applications usinglarge data sets beyond the laboratory environment. The dissertation alsoconcludes with a summary of the implications of these findings for subsequentresearch and future prospects in the field.

Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives