ConferenceCall 2023 10 18 - Revision history

Forum at 20:55, 16 February 2024

2024-02-16T20:55:57Z

← Older revision		Revision as of 20:55, 16 February 2024
Line 18:		Line 18:
	\|}		\|}

	= [[~~OntologySummit2024~~\|Ontology Summit 2024]] {{#show:{{PAGENAME}}\|?session}} =		= [[OntologySummit2024_FallSeries\|Ontology Summit 2024 Fall Series]] {{#show:{{PAGENAME}}\|?session}} =

	== Agenda ==		== Agenda ==
Line 248:		Line 248:
	\|?\|?Session\|mainlabel=-\|order=asc\|limit=3}}		\|?\|?Session\|mainlabel=-\|order=asc\|limit=3}}

	[[Category:~~OntologySummit2024~~]]		[[Category:OntologySummit2024_FallSeries]]
	[[Category:Icom_conf_Conference]]		[[Category:Icom_conf_Conference]]
	[[Category:Occurrence\| ]]		[[Category:Occurrence\| ]]

AndreaWesterinen: /* Participants */

2023-11-12T23:24:20Z

Participants

← Older revision		Revision as of 23:24, 12 November 2023
Line 61:		Line 61:
	* Yishan Liu		* Yishan Liu
	* James Logan		* James Logan
			* Jason Polis
			* Piers Hollott
	* [[PennyAnderson\|Penny Anderson]]		* [[PennyAnderson\|Penny Anderson]]
	* Michael Robbins		* Michael Robbins

Forum: /* Resources */

2023-11-08T21:06:34Z

Resources

← Older revision		Revision as of 21:06, 8 November 2023
Line 236:		Line 236:
	* [https://bit.ly/46A3EH2 Tony Seale Slides]		* [https://bit.ly/46A3EH2 Tony Seale Slides]
	* [https://bit.ly/46DJyvo Video Recording]		* [https://bit.ly/46DJyvo Video Recording]
			* [https://youtu.be/TAjkzg_lhVo YouTube Video]

	== Previous Meetings ==		== Previous Meetings ==

AndreaWesterinen: /* Discussion */

2023-11-04T04:26:59Z

Discussion

← Older revision		Revision as of 04:26, 4 November 2023
Line 77:		Line 77:
	** [[MikeBennett\|Mike Bennett]]: Dang! Put on a session on AI and the AIs start showing up!		** [[MikeBennett\|Mike Bennett]]: Dang! Put on a session on AI and the AIs start showing up!

	* [[AndreaWesterinen\|Andrea Westerinen]]: I like the quote, “Ontologies are the shapes of information and knowledge”. Also provide "information for communication".		* [[AndreaWesterinen\|Andrea Westerinen]]: I like the quote, “Ontologies are the shapes of information and knowledge”. Also they provide "information for communication".

	* [[ToddSchneider\|Todd Schneider]]: What is a ‘shape of information’?		* [[ToddSchneider\|Todd Schneider]]: What is a ‘shape of information’?

AndreaWesterinen: /* Discussion */

2023-11-04T01:51:34Z

Discussion

Forum: /* Resources */

2023-10-25T19:05:14Z

Resources

← Older revision		Revision as of 19:05, 25 October 2023
Line 229:		Line 229:

	== Resources ==		== Resources ==
			* [https://bit.ly/3S040lR Kurt Cagle Slides]
			* [https://bit.ly/46A3EH2 Tony Seale Slides]
	* [https://bit.ly/46DJyvo Video Recording]		* [https://bit.ly/46DJyvo Video Recording]

AndreaWesterinen: /* Agenda */

2023-10-23T03:17:15Z

Agenda

← Older revision		Revision as of 03:17, 23 October 2023
Line 28:		Line 28:
	** '''Title:''' How Ontologies Can Unlock the Potential of Large Language Models for Business		** '''Title:''' How Ontologies Can Unlock the Potential of Large Language Models for Business
	** '''Abstract:''' LLMs have remarkable capabilities; they can craft letters, analyze data, orchestrate workflows, generate code, and much more. Companies such as Google, Apple, Amazon, Meta, and Microsoft are all investing heavily in this technology. Everything indicates that LLMs have enormous disruptive potential. However, there is a problem: they can hallucinate, and for any serious business, that is a deal-breaker. This is where ontologies can come in. In combination with Knowledge Graphs, they can place guardrails around the LLMs, thus allowing organizations to harness the capabilities of LLMs within the framework of a safely controlled ontological structure.		** '''Abstract:''' LLMs have remarkable capabilities; they can craft letters, analyze data, orchestrate workflows, generate code, and much more. Companies such as Google, Apple, Amazon, Meta, and Microsoft are all investing heavily in this technology. Everything indicates that LLMs have enormous disruptive potential. However, there is a problem: they can hallucinate, and for any serious business, that is a deal-breaker. This is where ontologies can come in. In combination with Knowledge Graphs, they can place guardrails around the LLMs, thus allowing organizations to harness the capabilities of LLMs within the framework of a safely controlled ontological structure.
			** [https://bit.ly/46A3EH2 Slides]
	[https://bit.ly/46A3EH2 Slides]

	[https://bit.ly/46DJyvo Video Recording]		[https://bit.ly/46DJyvo Video Recording]

AndreaWesterinen: /* Participants */

2023-10-23T03:02:26Z

Participants

@@ Line 41: / Line 41: @@
 == Participants ==
 * Kurt Cagle
 * Tony Seale
 * [[KenBaclawski|Ken Baclawski]]
 == Discussion ==

AndreaWesterinen: /* Participants */

2023-10-23T02:51:43Z

Participants

← Older revision		Revision as of 02:51, 23 October 2023
Line 41:		Line 41:

	== Participants ==		== Participants ==
			* Kurt Cagle
			* Tony Seale
			* [[KenBaclawski\|Ken Baclawski]]

	== Discussion ==		== Discussion ==

AndreaWesterinen: /* Discussion */

2023-10-23T02:51:06Z

Discussion

Show changes

← Older revision		Revision as of 04:26, 4 November 2023
Line 77:		Line 77:
	** [[MikeBennett\|Mike Bennett]]: Dang! Put on a session on AI and the AIs start showing up!		** [[MikeBennett\|Mike Bennett]]: Dang! Put on a session on AI and the AIs start showing up!

	* [[AndreaWesterinen\|Andrea Westerinen]]: I like the quote, “Ontologies are the shapes of information and knowledge”. Also provide "information for communication".		* [[AndreaWesterinen\|Andrea Westerinen]]: I like the quote, “Ontologies are the shapes of information and knowledge”. Also they provide "information for communication".

	* [[ToddSchneider\|Todd Schneider]]: What is a ‘shape of information’?		* [[ToddSchneider\|Todd Schneider]]: What is a ‘shape of information’?

← Older revision		Revision as of 01:51, 4 November 2023
Line 77:		Line 77:
	** [[MikeBennett\|Mike Bennett]]: Dang! Put on a session on AI and the AIs start showing up!		** [[MikeBennett\|Mike Bennett]]: Dang! Put on a session on AI and the AIs start showing up!

	* [[AndreaWesterinen\|Andrea Westerinen]]: I like the quote, “Ontologies are the shapes of information and knowledge”		* [[AndreaWesterinen\|Andrea Westerinen]]: I like the quote, “Ontologies are the shapes of information and knowledge”. Also provide "information for communication".

	* [[ToddSchneider\|Todd Schneider]]: What is a ‘shape of information’?		* [[ToddSchneider\|Todd Schneider]]: What is a ‘shape of information’?
Line 110:		Line 110:

	* [[RaviSharma\|Ravi Sharma]]: Kurt when you talk of box, you are essentially stating in and out of scope items or is there a way of capturing the info outside the box and bringing it in?		* [[RaviSharma\|Ravi Sharma]]: Kurt when you talk of box, you are essentially stating in and out of scope items or is there a way of capturing the info outside the box and bringing it in?

			* [[AndreaWesterinen\|Andrea Westerinen]]: "What is valid for a graph? Shapes and data"

	* [[MichaelDeBellis\|Michael DeBellis]]: I don't agree that knowledge graphs are a form of data mesh. They are two related but different concepts. Data mesh is essentially an architecture for enterprise data definition and management. Knowledge graphs are a tool that can be used to implement a data mesh. Data mesh IMO brings the philosophy of microservices to data.		* [[MichaelDeBellis\|Michael DeBellis]]: I don't agree that knowledge graphs are a form of data mesh. They are two related but different concepts. Data mesh is essentially an architecture for enterprise data definition and management. Knowledge graphs are a tool that can be used to implement a data mesh. Data mesh IMO brings the philosophy of microservices to data.
Line 148:		Line 150:
	* Kurt Cagle: Once you load in the ontology into a conversation, it will create (to some extent) an LLM conceptual space for that data. Also keep in mind that getting ALL of a knowledge graph via a RAG is usually not feasible.		* Kurt Cagle: Once you load in the ontology into a conversation, it will create (to some extent) an LLM conceptual space for that data. Also keep in mind that getting ALL of a knowledge graph via a RAG is usually not feasible.

	* [[RaviSharma\|Ravi Sharma]]: Tony great diagram for LLM ontology ~~lop~~ to improve each other.why is ontology weak in capturing concepts Vs LLM?		* [[RaviSharma\|Ravi Sharma]]: Tony great diagram for LLM + ontology to improve each other.why is ontology weak in capturing concepts Vs LLM?

	* [[MichaelDeBellis\|Michael DeBellis]]: One of the most interesting papers I've read is from Lawrence Berkeley Labs on using LLMs to extend an ontology.		* [[MichaelDeBellis\|Michael DeBellis]]: One of the most interesting papers I've read is from Lawrence Berkeley Labs on using LLMs to extend an ontology.
Line 156:		Line 158:
	** Michael Robbins: https://writings.stephenwolfram.com/2023/03/chatgpt-gets-its-wolfram-superpowers/		** Michael Robbins: https://writings.stephenwolfram.com/2023/03/chatgpt-gets-its-wolfram-superpowers/

	* [[RaviSharma\|Ravi Sharma]]: Tony the built-in ~~ubcertainty~~ in LLMs gives it extra power to apply to real life probabilistic world?		* [[RaviSharma\|Ravi Sharma]]: Tony the built-in uncertainty in LLMs gives it extra power to apply to real life probabilistic world?

	* [[RaviSharma\|Ravi Sharma]]: Tony LLMs and analog and ontology as Quantum? great way. thanks		* [[RaviSharma\|Ravi Sharma]]: Tony LLMs and analog and ontology as Quantum? great way. thanks
Line 163:		Line 165:
	** [[GaryBergCross\|Gary Berg-Cross]]: A better model than left right hemispheres is by layers - old, mid brain (associative) and neo-cortex. They interconnect in many ways and some by the limbic system.		** [[GaryBergCross\|Gary Berg-Cross]]: A better model than left right hemispheres is by layers - old, mid brain (associative) and neo-cortex. They interconnect in many ways and some by the limbic system.
	** [[BartGajderowicz\|Bart Gajderowicz]]: I like the System 1 / System 2 analogy		** [[BartGajderowicz\|Bart Gajderowicz]]: I like the System 1 / System 2 analogy

			* [[AndreaWesterinen\|Andrea Westerinen]]: Tony characterized knowledge graphs as discrete and LLMs as continuous.

	* Cedric Berger: Aren’t LLMs also kind of discrete as relying on vectors (arrays of numbers) of limited dimensions?		* Cedric Berger: Aren’t LLMs also kind of discrete as relying on vectors (arrays of numbers) of limited dimensions?