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

Although AI systems have been applied in various fields and achievedimpressive performance, their safety and reliability are still a big concern.This is especially important for safety-critical tasks. One sharedcharacteristic of these critical tasks is their risk sensitivity, where smallmistakes can cause big consequences and even endanger life. There are severalfactors that could be guidelines for the successful deployment of AI systems insensitive tasks: (i) failure detection and out-of-distribution (OOD) detection;(ii) overfitting identification; (iii) uncertainty quantification forpredictions; (iv) robustness to data perturbations. These factors are alsochallenges of current AI systems, which are major blocks for building safe andreliable AI. Specifically, the current AI algorithms are unable to identifycommon causes for failure detection. Furthermore, additional techniques arerequired to quantify the quality of predictions. All these contribute toinaccurate uncertainty quantification, which lowers trust in predictions. Henceobtaining accurate model uncertainty quantification and its further improvementare challenging. To address these issues, many techniques have been proposed,such as regularization methods and learning strategies. As vision and languageare the most typical data type and have many open source benchmark datasets,this thesis will focus on vision-language data processing for tasks likeclassification, image captioning, and vision question answering. In thisthesis, we aim to build a safeguard by further developing current techniques toensure the accurate model uncertainty for safety-critical tasks.

Building Safe and Reliable AI systems for Safety Critical Tasks with Vision-Language Processing