Item:OSW3dc790110508459489f954080a7bcb65: Difference between revisions

From Battery Knowledge Base
Item:OSW3dc790110508459489f954080a7bcb65
mNo edit summary
mNo edit summary
 
(One intermediate revision by the same user not shown)
Line 1: Line 1:
The event featured a talk from Dr. Simon Clark with the title, "{{Template:Viewer/Link|page=File:OSWe27032521f0b4d669eaa6e6f585ace46.pdf|url=|label=Putting the AI in FAIR: How Ontologies Unlock Battery Knowledge for the Agentic Era}}"
The event featured a talk from {{Template:Viewer/Link|page=Item:OSW72e733f317ef4cf9b8ca53e906c9acb9|url=|label=Dr. Simon Clark}} with the title, "{{Template:Viewer/Link|page=File:OSWe27032521f0b4d669eaa6e6f585ace46.pdf|url=|label=Putting the AI in FAIR: How Ontologies Unlock Battery Knowledge for the Agentic Era}}"


Abstract: As AI systems become more autonomous, they require structured and machine-actionable knowledge to reason, plan, and make informed decisions. Ontologies provide the semantic foundation that enables AI to work with battery data beyond simple pattern recognition-allowing for automated reasoning and cross-domain integration. While large language models (LLMs) can extract insights from unstructured data, they lack explicit relationships, logical constraints, and the ability to perform reliable, standards-based reasoning. By embedding battery knowledge into FAIR (Findable, Accessible, Interoperable, and Reusable) ontologies, we enable AI to move from text prediction to intelligent action and drive new breakthroughs in battery science.
Abstract: As AI systems become more autonomous, they require structured and machine-actionable knowledge to reason, plan, and make informed decisions. Ontologies provide the semantic foundation that enables AI to work with battery data beyond simple pattern recognition-allowing for automated reasoning and cross-domain integration. While large language models (LLMs) can extract insights from unstructured data, they lack explicit relationships, logical constraints, and the ability to perform reliable, standards-based reasoning. By embedding battery knowledge into FAIR (Findable, Accessible, Interoperable, and Reusable) ontologies, we enable AI to move from text prediction to intelligent action and drive new breakthroughs in battery science.
jsondata
Line 27: Line 27:
     "attachments": [
     "attachments": [
         "File:OSWe27032521f0b4d669eaa6e6f585ace46.pdf"
         "File:OSWe27032521f0b4d669eaa6e6f585ace46.pdf"
    ],
    "project": [
        "Item:OSW6499d04ced9649f8bbc50f1e940a50c8"
     ]
     ]
}
}

Latest revision as of 11:38, 28 May 2025

POLiS Seminar May 2025
ID OSW3dc790110508459489f954080a7bcb65
UUID 3dc79011-0508-4594-89f9-54080a7bcb65
Label POLiS Seminar May 2025
Machine compatible name PolisSeminarMay2025
Statements (outgoing)
Statements (incoming)
Keywords webinar

Description


📎 Select files (or drop them here)... 📷 Camera
    jsondata
    type
    "Category:OSW0e084decca6f48a7b023d6b7b2c1452d"
    uuid"3dc79011-0508-4594-89f9-54080a7bcb65"
    label
    text"POLiS Seminar May 2025"
    lang"en"
    description
    text"An online seminar of the POLiS cluster"
    lang"en"
    keywords
    "Item:OSW33726bfbbe21401a9416b4112fa96f8b"
    start_date"2025-05-28"
    end_date"2025-05-28"
    participants
    "Item:OSW72e733f317ef4cf9b8ca53e906c9acb9"
    name"PolisSeminarMay2025"
    attachments
    "File:OSWe27032521f0b4d669eaa6e6f585ace46.pdf"
    project
    "Item:OSW6499d04ced9649f8bbc50f1e940a50c8"
    Cookies help us deliver our services. By using our services, you agree to our use of cookies.