• Aucun résultat trouvé

On The Role of Knowledge Graphs in Explainable AI

N/A
N/A
Info
Télécharger
Protected

Academic year: 2022

Partager "On The Role of Knowledge Graphs in Explainable AI"

Copied!
1
0
0

Chargement.... (Voir le texte intégral maintenant)

Texte intégral

(1)

On The Role of Knowledge Graphs in Explainable AI

Freddy Lecue

CortAIx (Centre of Research & Technology in Artificial Intelligence eXpertise) Montr´eal, Kanada

freddy.lecue@inria.fr

Abstract. The current hype of Artificial Intelligence (AI) mostly refers to the success of machine learning and its sub-domain of deep learning.

However, AI is also about other areas, such as Knowledge Representation and Reasoning, or Distributed AI, i.e., areas that need to be combined to reach the level of intelligence initially envisioned in the 1950s. Ex- plainable AI (XAI) now refers to the core backup for industry to apply AI in products at scale, particularly for industries operating with critical systems. XAI can not only be reviewed from a Machine Learning per- spective, but also from the other AI research areas, such as AI Planning or Constraint Satisfaction and Search. We expose the XAI challenges of AI fields, their existing approaches, limitations and the great opportuni- ties for Semantic Web Technologies and Knowledge Graphs to push the boundaries of XAI further.

Copyrightc 2019 for this paper by its authors. Use permitted under Creative Com- mons License Attribution 4.0 International (CC BY 4.0).

Références

Télécharger maintenant ( PDF - 1 Page - 143.37 KB )

Documents relatifs

Sensor Networks in the Wild: Challenges and opportunities for Semantic Web technologies

As data is collected we need to record its context so that it may be properly interpreted, and when it is published we need to know its provenance so that we can understand quality

The Butterfly Effect in Knowledge Graphs: Predicting the Impact of Changes in the Evolving Web of Data

I plan to investigate this question in practical settings by studying: (1) KGs of different topics, maintenance processes, size, and structure; (2) features por- traying

Integrating Knowledge Graphs for Comparing the Scientific Output of Academia and Industry

The preliminary approach presented in this paper integrates data from several knowledge graphs describing scientific articles (Microsoft Academics Graph), research

RDF Explorer: A Visual Query Builder for Semantic Web Knowledge Graphs

Figure 1 provides a screenshot of the interface for querying Wikidata, where we can see three components: a search panel (left pane), a visual query editor (center pane), a node

Feeding Machine Learning with Knowledge Graphs for Explainable Object Detection

(2) For each prediction with an initial score higher than s t , we derive a trustworthy indicator: it should indicate if the context (mean- ing the other detections on the image)

The Case for Contextualized Knowledge Graphs in Air Traffic Management

In particular, we illustrate how the temporality concept of the Aeronautical Information Exchange Model is represented using contextualized knowledge graphs with a temporal

Explainable Entity-based Recommendations with Knowledge Graphs

Our method jointly ranks items and knowledge graph entities using a Personalized PageRank procedure to produce recommendations together with their explanations..

Semantic Knowledge and Privacy in the Physical Web

In our work, we use Semantic Web technology through an ontology to define a hierarchical context model for a user and a requester an rules are defined using the Semantic Web