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

Machine Learning (ML) has emerged as a powerful form of data modelling withwidespread applicability beyond its roots in the design of autonomous agents.However, relatively little attention has been paid to the interaction betweenpeople and ML systems. In this paper we view interaction between humans and MLsystems within the broader context of communication between agents capable ofprediction and explanation. We formalise the interaction model by taking agentsto be automata with some special characteristics and define a protocol forcommunication between such agents. We define One- and Two-Way Intelligibilityas properties that emerge at run-time by execution of the protocol. Theformalisation allows us to identify conditions under which run-time sequencesare bounded, and identify conditions under which the protocol can correctlyimplement an axiomatic specification of intelligible interaction between ahuman and an ML system. We also demonstrate using the formal model to: (a)identify instances of One- and Two-Way Intelligibility in literature reports onhumans interacting with ML systems providing logic-based explanations, as isdone in Inductive Logic Programming (ILP); and (b) map interactions betweenhumans and machines in an elaborate natural-language based dialogue-model toOne- or Two-Way Intelligible interactions in the formal model.

A Model for Intelligible Interaction Between Agents That Predict and Explain