Re: AI KR Strategist, explainabiilty, state of the art

I have recently (well a year or two ago) update the wiki a bit
but I guess updates should me ,made more regularly
Whatever members wish to discuss/contribute, should be aligned
Something like
Intelligence (reasoning, cognition)
ML/AI to achieve intelligence
KR (techniques, methods) as explicit/accountable/verifiability AI/a
mechanisms for explainability (the explicit representation of AI
processes/outcomes)

I simply would like to encourage alignment, so that each contribution can
find its place

Rendering the resources into machine readable format is useful, but the
core challenges in AI (such as explainability), and how KR contributes to
solve them, are more complex and remain high priority,

Let's keep that requirement for alignment in mind in meeting agendas
(repeat: ai challenges(aka explainability)/kr solutions)

I may be able to contribute a pre recorded talk on my current work on
explainability, if of interest, as an agenda item for the meetings (in
person meetings time is generall short)

 If would be great if CG members could also start putting together some
ideas so that when Carl gets around to do meetings, people can bring up
their points either live or via short notes (I hope that Carl can include
in the meeting minutes)

So Carl, could you perhaps start an agenda on the wiki that people can
start adding items for discussion to? would that be a good idea?
(My items for discussion are the points above)

cheers

P

P



On Sun, Nov 10, 2024 at 12:35 AM Peter Rivett <
pete.rivett@federatedknowledge.com> wrote:

>
> I wouldn't say what we have from 2018 on our homepage
> https://www.w3.org/groups/cg/aikr/ as a list of "proposed outcomes"
> (mirrored in the StratML version) was ever what I'd call a plan. If what
> you're saying is the homepage should be updated to reflect what we're
> actually doing then that makes sense. If only to attract others who might
> be interested in our actual work.
> I think what Paola has summarized as challenges in this thread already
> provides a reasonable start.
>
> Carl started asking for expressions of interest. Again, I'm expressing
> interest in *KR to support explainable AI.* I'm not interested in Role
> Descriptions, Strategy Formulations or structured Plans. And not, for now
> as [part of this Group, the other 6 of the 7 items that Carl listed.
>
> Cheers
> Pete
>
> PS I guess the homepage should also link to the AI KR Strategist Role
> Description already produced (though not sure how that fits).
>
>
> Pete Rivett (pete.rivett@federatedknowledge.com)
> Federated Knowledge, LLC (LEI 98450013F6D4AFE18E67)
> tel: +1-701-566-9534
> Schedule a meeting at https://calendly.com/rivettp
>
> ------------------------------
> *From:* Owen Ambur <owen.ambur@verizon.net>
> *Sent:* Saturday, November 9, 2024 8:23 AM
> *To:* Paola Di Maio <paoladimaio10@gmail.com>; carl mattocks <
> carlmattocks@gmail.com>
> *Cc:* W3C AIKR CG <public-aikr@w3.org>
> *Subject:* Re: AI KR Strategist, explainabiilty, state of the art
>
> From my perspective, this exchange might be more productive if it focused
> directly on the elements of the plan, if any, that we aim to craft and
> pursue together.
>
> At this point, I am unable to decipher those elements from this exchange
> of E-mail messages.  It reminds me of an assertion relating to the
> Capability Maturity Model (CMM):
>
> E-mail is a stage of immaturity through which we must pass.
>
>
> Plans previously considered by the AIKR CG are available in StratML format
> at https://stratml.us/drybridge/index.htm#AIKRCG
>
> Perhaps we might at least revisit and perhaps update this one:
> https://stratml.us/docs/AIKRCG.xml
>
> It would be nice to report any progress that may have been made on any of
> the objectives it sets forth for us.
>
> It is available for comments at
> https://stratml.us/carmel/iso/part2/AIKRCGforComment.xml and for editing
> in StratML Part 2, Performance Plan/Report, format at
> https://stratml.us/drybridge/index.htm#AIKRCG
>
> Owen Ambur
> https://www.linkedin.com/in/owenambur/
>
>
> On Saturday, November 9, 2024 at 07:34:28 AM EST, carl mattocks <
> carlmattocks@gmail.com> wrote:
>
>
> Paola
>
> To be explicit ... I am not proposing to focus exclusively on  Explainable
> Artificial Intelligence
> <https://www.darpa.mil/program/explainable-artificial-intelligence> (a
> suite of machine learning techniques that: Produce more explainable models
>  )
> I do expect to have discussions about models used in the explanations
> about KR used in AI.
>
> cheers
>
> Carl
>
>
> It was a pleasure to clarify
>
>
> On Sat, Nov 9, 2024 at 2:10 AM Paola Di Maio <paoladimaio10@gmail.com>
> wrote:
>
> Carl,
> following my earlier email response, let me make explicit (...)
> a fundamental point that perhaps came across as implied (...)
>
> misrepresentation  miscategorization  correctness
> transparency, accountability,reliability verifiability
> and all sorts of AI flaws and errors  = AI challenges
>  can be addressed at least in part with KR
> and mitigated through explainability
> however
> and that the  field of XAI, based on a review of the state of the art,
> has become paradoxically inextricable  and unexplainable in its own right
>
> Proposed approaches must tackle directly the challenges, and possibly be
> supported with some evidence/proof of their effectiveness
> (usefulness notwithstanding)
>
> P
>
> s, or making AI more transparent, more reliable, more accountable
> that
>
> On Sat, Nov 9, 2024 at 12:42 AM carl mattocks <carlmattocks@gmail.com>
> wrote:
>
> Paola
>
> Please note in the email chain there are statements about 'explainability'
> which continues to be an issue . .. thus the focus of the proposed effort.
>
> Carl
>
> On Fri, Nov 8, 2024, 5:41 PM Paola Di Maio <paola.dimaio@gmail.com> wrote:
>
> Carl, good to hear from you and thanks
> for picking up where you left .
>
> Btw the attachment you sent never made it into W3C Group reports, maybe at
> some point you d like to publish them with some notes explaining how these
> addressed the challenges discussed? The documents you send do not seem to
> explain how the proposed work fits in the AI KR mission (which problem they
> solve).
>
> As previously discussed StratML can be a useful mechanism represent
> knowledge, at syntactic level. A markup language by itself it does not
> address nor resolve the key challenges faced by AI today that KR (thinking
> semantics here) as a whole could tackle. (irrespective of any
> implementation language of choice).
>
> In the work you propose, there is strong coupling between AI KR and
> StratML as a syntax
> (your construct binds the two) This approach may be suitable in a Stratml
> CG (is the one by the way)? rather than an AI KR CG  The focus is AI KR,
> rather than a modeling language by itself
>
> If the line you are interested to explore is StratML only, it could be
> useful if you (or other proponents of this line of work) could  summarise
> how it address the broader AI KR challenges.
> For example, say, knowledge misrepresentation - or miscategorization - or
> wrong recommendations, or making AI more transparent, more reliable, more
> accountable etc.
>
> Perhaps  show how these can be addressed  with use cases or other proof of
> concept.
>
> So basically, I encourage discussions to be focused on AI KR  and whatever
> line of work members propose, please make it clear which problem each
> construct intends to resolve in relation to the overall mission.
>
> Thank  you!
>
> Paola Di Maio, PhD
>
>
> On Thu, Nov 7, 2024 at 6:09 PM carl mattocks <carlmattocks@gmail.com>
> wrote:
>
> Greetings All - It has been a while.
>
> Given the interest in AI , I am proposing that we set up a series of
> online meetings to expand on the AI Strategist work that focused on
> leveraging StratML. (see attached).
>
> The topics include:
>
>    1. AI Observability Mechanisms (monitor behavior, data, and
>    performance)
>    2. KR Models used in the explanations (to a given audience, and what
>    concepts are needed for this)
>    3. KR ID needed for Knowledge Content (UID, URI) Logistics management
>    4. Roles of Humans in the Loop (as a creator, and an audience type)
>    5. Agents having Authority awarded by a Human in the Loop
>    6. Catalogs of AI capabilities ( see Data Catalog (DCAT) Vocabulary
>    <https://www.w3.org/TR/vocab-dcat-3/> )
>    7. AIKR Using / Used in DPROD (specification provides unambiguous and
>    sharable semantics) https://ekgf.github.io/dprod/
>
>
> Timeslots for meetings  will be determined by participants.  Please let me
> know if you are interested.
>
> Thanks
>
> Carl Mattocks
>
> CarlMattocks@WellnessIntelligence.Institute
> It was a pleasure to clarify
>
>
> On Tue, Jun 11, 2024 at 5:24 AM Dave Raggett <dsr@w3.org> wrote:
>
> First my thanks to Paola for this CG. I’m hoping we can attract more
> people with direct experience. Getting the CG noticed more widely is quite
> a challenge! Any suggestions?
>
> It has been proposed that without knowledge representation. there cannot
> be AI explainability
>
>
> That sounds somewhat circular as it presumes a shared understanding of
> what “AI explainability” is.  Humans can explain themselves in ways that
> are satisfactory to other humans.  We’re now seeing a similar effort to
> enable LLMs to explain themselves, despite having inscrutable internal
> representations as is also true for the human brain.
>
> I would therefore suggest that for explainability, knowledge
> representation is more about the models used in the explanations rather
> than in the internals of an AI system. Given that, we can discuss what
> kinds of explanations are effective to a given audience, and what concepts
> are needed for this.
>
> Explanations further relate to how to making an effective argument that
> convinces people to change their minds.  This also relates to the history
> of work on rhetoric, as well as to advertising and marketing!
>
> Best regards,
>
> Dave Raggett <dsr@w3.org>
>
>
>
>