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

Recent advances in machine learning, particularly deep learning, have enabledautonomous systems to perceive and comprehend objects and their environments ina perceptual subsymbolic manner. These systems can now perform objectdetection, sensor data fusion, and language understanding tasks. However, thereis a growing need to enhance these systems to understand objects and theirenvironments more conceptually and symbolically. It is essential to considerboth the explicit teaching provided by humans (e.g., describing a situation orexplaining how to act) and the implicit teaching obtained by observing humanbehavior (e.g., through the system's sensors) to achieve this level of powerfulartificial intelligence. Thus, the system must be designed with multimodalinput and output capabilities to support implicit and explicit interactionmodels. In this position paper, we argue for considering both types of inputs,as well as human-in-the-loop and incremental learning techniques, for advancingthe field of artificial intelligence and enabling autonomous systems to learnlike humans. We propose several hypotheses and design guidelines and highlighta use case from related work to achieve this goal.

Adaptive User-centered Neuro-symbolic Learning for Multimodal Interaction with Autonomous Systems