June 2024 - CG - lists.cs.uni-kassel.de

by Jon Awbrey

Logical Graphs • Discussion 5 • https://inquiryintoinquiry.com/2023/08/28/logical-graphs-discussion-5/ Re: Logical Graphs • First Impressions • https://inquiryintoinquiry.com/2023/08/24/logical-graphs-first-impressions/ Re: Facebook • Daniel Everett • https://www.facebook.com/permalink.php?story_fbid=pfbid026jD3t75k69Wbs9q3qa… DE: Nice discussion. Development of icon-based reasoning. My Comment — As it happens, even though Peirce's systems of logical graphs do have iconic features, their real power over other sorts of logical diagrams (like venn diagrams) is due to their deeper symbolic character. Thereby will hang many tales to come … Regards, Jon cc: https://www.academia.edu/community/VjWX8L cc: https://mathstodon.xyz/@Inquiry/110967659414575933

1 month, 3 weeks

1
6
0 0

Google AI does not understand satire

by John F Sowa

Following is an offline email note that shows why nobody is using LLMs to check Social Media for notes that should be deleted or flagged as dangerous for one reason or another. That is a very important application that would be worth a huge amount of money if it could be done accurately. John _____________ On Jun 15, 2024, John F Sowa wrote: But Google AI does not understand satire. On Jun 16, 2024 XXX wrote: Or sarcasm, humor, anger, internet flame wars, stupidity, poetry, hunger or any other emotion or part of being intelligent or self-conscious. Turns out that a gussied up autocorrect doesn’t handle subtlety. Who knew? No one knew it was that hard. What is an emotion? https://www.gocomics.com/doonesbury/1974/09/20

4 months, 2 weeks

1
0
0 0

Theme One Program • Jets and Sharks

by Jon Awbrey

Theme One Program • Jets and Sharks 1 • https://inquiryintoinquiry.com/2024/06/20/theme-one-program-jets-and-sharks… All, It is easy to spend a long time on the rudiments of learning and logic before getting down to practical applications — but I think we've circled square one long enough to expand our scope and see what the category of programs envisioned in Theme One can do with more substantial examples and exercises. During the development of the Theme One program I tested successive implementations of its Reasoning Module or Logical Modeler on examples of logical problems current in the literature of the day. The PDP Handbook of McClelland and Rumelhart set one of the wittiest gems ever to whet one's app‑titude so I could hardly help but take it on. The following text is a light revision of the way I set it up in the program's User Guide. Example 5. Jets and Sharks — The propositional calculus based on “minimal negation operators” can be interpreted in a way resembling the logic of activation states and competition constraints in one class of neural network models. One way to do this is to interpret the blank or unmarked state as the resting state of a neural pool, the bound or marked state as its activated state, and to represent a mutually inhibitory pool of neurons A, B, C by the minimal negation proposition (A , B , C). The manner of representation may be illustrated by transcribing a well‑known example from the parallel distributed processing literature (McClelland and Rumelhart 1988) and working through a couple of the associated exercises as translated into logical graphs. Minimal Negation Operators • https://oeis.org/wiki/Minimal_negation_operator Displayed below is the text expression of a traversal string which Theme One parses into a cactus graph data structure in computer memory. The cactus graph represents a single logical formula in propositional calculus and this proposition embodies all the logical constraints defining the Jets and Sharks data base. Theme One Guide • Jets and Sharks • Log File • https://inquiryintoinquiry.files.wordpress.com/2022/08/theme-one-guide-e280… References — • McClelland, J.L. (2015), Explorations in Parallel Distributed Processing : A Handbook of Models, Programs, and Exercises, 2nd ed. (draft), Stanford Parallel Distributed Processing Lab. ( https://web.stanford.edu/group/pdplab/ ) ( https://web.stanford.edu/group/pdplab/pdphandbook/ ) Section 2.3 ( https://web.stanford.edu/group/pdplab/pdphandbook/handbookch3#x7-320002.3 ) Figure 2.1 ( https://web.stanford.edu/group/pdplab/pdphandbook/jetsandsharkstable.png ) • McClelland, J.L., and Rumelhart, D.E. (1988), Explorations in Parallel Distributed Processing : A Handbook of Models, Programs, and Exercises, MIT Press, Cambridge, MA. “Figure 1. Characteristics of a number of individuals belonging to two gangs, the Jets and the Sharks”, p. 39, from McClelland (1981). • McClelland, J.L. (1981), “Retrieving General and Specific Knowledge From Stored Knowledge of Specifics”, Proceedings of the Third Annual Conference of the Cognitive Science Society, Berkeley, CA. Regards, Jon cc: https://www.academia.edu/community/VWYGZo

4 months, 2 weeks

1
2
0 0

Principia Logico-Metaphysica by Edward N. Zalta

by John F Sowa

Alex, Thanks for that info. Zalta's Principia is a huge compendium (1501 pages with more to come) of formal definitions and proofs. The Isabelle theorem prover is an excellent basis for automated reasoning with and about anything that uses those definitions. And the supporting software can be downloaded for free. As I said before, I was highly skeptical about any formal definitions developed in Ontolog Forum, because this is not a standards organization. However, if the definitions are taken from or based on Zalta's Principia and supported by Isabelle, they can be posted in web pages shared by anybody and everybody. I'm sure that Stanford would support or collaborate with anybody who develops such a repository. Re Top-Level Ontologies: The TLOs are specified in very restricted formats in a tiny subset of first-order logic. Isabelle supports all of FOL plus much, much more. As I have been pointing out, FOL is much simpler, more general, easier to use, and faster than OWL2. The availability of Isabelle with all of the definitions in Zalta's tome would make a strong argument for OWL3 (the same notation for the hierarchy as OWL2, but full FOL as an upgrade). There is a question about Common Logic, which is a different extension to FOL, I believe that the HeTS tools could be extended to support mappings of CL to and from Isabelle. There are various issues about the mappings, and HeTS is sufficiently general that it could be extended to support them. Any TLO specified in OWL can be automatically mapped to FOL (the extension to OWL3) and used with anything specified in the Zalta's system. Although Isabelle supports HOL, a large majority of the structures defined by Zalta use only the FOL subset. Common Logic is a different extension to FOL. The HeTS tools and the OMG standard for DOL could be used to do the mappings. Since Isabelle also supports FOL as a subset, it would be a good tool for supporting OWL3. That's another argument for getting rid of the limitations and exceptions of OWL2 and move to OWL3. Existing applications that use OWL2 would not be affected. But new applications could use the simpler OWL3 notation. For more about Isabelle and links to resources, see the Wikipedia page: https://en.wikipedia.org/wiki/Isabelle_(proof_assistant) . John _______________________________________ From: "alex.shkotin" <alex.shkotin(a)gmail.com> Colleagues, Edward N. Zalta is well known for to be co-principal editor of https://plato.stanford.edu/info.html . I just got the URL to his axiomatic theory https://mally.stanford.edu/principia.pdf may be interesting to compare with TLOs. It is not only axiomatic but formalized one using Isabelle/HOL. Alex

4 months, 2 weeks

1
0
0 0

Re: [ontolog-forum] Why ChatGPT does not trust itself as an author

by John F Sowa

Mike, I agree with your comments below. As I keep repeating, LLMs are an extremely valuable ADDITION to the AI toolkit. They have a wide variety of applications, especially for translating languages, natural and artificial. But they are an addition, not a replacement. Since "ontology' is the focus of this forum, I would emphasize the role of ontology in evaluating, testing, revising, and enhancing the output generated by LLMs. For reasoning, LLMs are an excellent method for abduction (guessing). But by themselves, they cannot do deduction, testing, and evaluation. They are able to find and apply certain patterns of deduction. and if their source data is limited to a single set of consistent statements, the results are usually correct. But "consistent" and "usually" are problematical. That is why we need methods that control how the results LLMs generate are tested, evaluated, and used. Kingsley does that. Wolfram does that. Our Permion.ai company does that. In fact, you do that when you work with LLM-based software and make your own decisions about what to use or ignore. There are many more options and combinations to explore. But it's important to remember that somebody or something must test and evaluate what to do with the LLM output. GOFAI (Good Old Fashioned AI) is not obsolete. John ________________________________________ From: "Mike Bergman" <mike(a)mkbergman.com> Hi All, In the sense of fairness by providing an alternative viewpoint, I prompted ChatGPT 4o (as of today) with the inverse question. I am not personally endorsing the practice, and I further believe any LLM used to support an academic (or other) manuscript should be disclosed as to how used, even if allowed by the publisher. Best, Mike

4 months, 3 weeks

1
0
0 0

Why ChatGPT does not trust itself as an author

by John F Sowa

I recommend the following article as an appendix to the Communiqué on the recent Ontology Summit. It is a succinct summary of the issues. John ____________________________ Why ChatGPT Should Not Be Used to Write Academic Scientific Manuscripts for PublicationThe Annals of Family Medicine, March 2023, 2958; DOI: https://doi.org/10.1370/afm.2982 Editor Caroline Richardson asked Chat GPT-4, OpenAI’s advanced language processing tool, about authoring scientific manuscripts. Prompt: Write a short editorial about why ChatGPT should not be used to write academic scientific manuscripts for publication. Response: A language model trained by OpenAI, ChatGPT is a remarkable tool that can generate coherent and grammatically correct text on a wide range of topics. However, when it comes to writing academic scientific manuscripts for publication, ChatGPT falls short in several critical ways. First and foremost, ChatGPT lacks the domain-specific knowledge and expertise that is essential for producing high quality scientific manuscripts. While it may be able to generate text that sounds plausible and coherent, it cannot provide the kind of nuanced and sophisticated analysis that is required for scientific research. This is especially true for research that involves complex statistical analyses, experimental design, and interpretation of results. Furthermore, ChatGPT cannot ensure the accuracy, validity, and reliability of scientific claims and findings. Scientific research depends on the rigorous collection and analysis of data, and the careful interpretation of results. This requires not only expertise in the relevant field of study, but also a keen eye for detail and a commitment to the highest standards of scientific rigor. Another key limitation of ChatGPT is its inability to engage in the iterative and collaborative process that is characteristic of scientific research. Writing a scientific manuscript is not a one-time event, but rather a process of continuous refinement and improvement. This process involves multiple rounds of feedback and revision, as well as collaboration with colleagues and reviewers to ensure that the final product meets the highest standards of quality. In conclusion, while ChatGPT may be a useful tool for generating ideas and basic drafts of text, it should not be relied upon for writing academic scientific manuscripts for publication. The complex and nuanced nature of scientific research requires the expertise and input of human researchers who can ensure the accuracy, validity, and reliability of scientific claims and findings, as well as engage in the iterative and collaborative process that is essential for producing high quality scientific manuscripts. Submitted March 20, 2023; accepted March 20, 2023. Disclaimer: This is the only time a chatbot will be allowed or cited as an author in Annals of Family Medicine. See our Policy on Authorship.

4 months, 3 weeks

1
0
0 0

Standards organizations (was Precise definitions for data... etc.

by John F Sowa

Folks, Many subscribers to Ontolog Forum, including me, are or have been working or collaborating with various standards organizations -- ISO, OMG, IEEE, etc. And many others have important ideas, requirements, or suggestions for standards of various kinds. But Ontolog Forum is not a standards organization, and any emails that anybody posts to Ontolog Forum will go no further than the Ontolog website. Anybody is free to use those suggestions, but they will have no official standing or certification of any kind. For theoretical issues about representations of any kind, first-order logic is fundamental. Anything that is specified in FOL is guaranteed to be absolutely precise to the finest detail. Furthermore, anything and everything implemented in or on any digital device of any kind can be specified in FOL. Therefore, I strongly recommend FOL as the foundation for specifying all computable representations of any kind. There are, however, some kinds of information that may require extensions to modal or higher order logics for certain kinds of features. Issues that go beyond FOL have been specified in logics, such as Common Logic and the IKL extensions to CL. But in every case, logic is fundamental. It's impossible to have a precise specification of anything that cannot be translated to and from FOL or to some formally defined logic that includes FOL as a proper subset. I know many of the Ontolog subscribers with whom I had been discussing these and related issues in meetings and email lists since I first began to work with standards organizations in the early 1990s. I'm sure that they can add much more info about these matters. Fundamental issue: It's pointless to waste large amounts of human time and computer cycles on discussion of standards without considering whether and how any of this discussion could be developed into international standards by some official standards organization(s). And FOL and/or some extensions to FOL should be the ultimate foundation for any of those standards. John PS: It's OK to use subsets of FOL for some purposes, since any subset can be translated to FOL. But FOL itself has a very clean and simple translation to and from natural languages with just seven common words: and, or, not, if-then, some, every. It is the ideal common representation for anything computable. Any specification in FOL can be accompanied by an automatically generated translation to any desired natural language.

4 months, 3 weeks

1
0
0 0

Theme One Program • Exposition

by Jon Awbrey

Theme One Program • Exposition 1 • https://inquiryintoinquiry.com/2024/06/09/theme-one-program-exposition-1-b/ All, Theme One is a program for building and transforming a particular species of graph‑theoretic data structures, forms designed to support a variety of fundamental learning and reasoning tasks. The program evolved over the course of an exploration into the integration of contrasting types of activities involved in learning and reasoning, especially the types of algorithms and data structures capable of supporting a range of inquiry processes, from everydayproblem solving to scientific investigation. In its current state, Theme One integrates over a common data structure fundamental algorithms for one type of inductive learning and one type of deductive reasoning. We begin by describing the class of graph‑theoretic data structures used by the program, as determined by their local and global aspects. It will be the usual practice to shift around and to view these graphs at many different levels of detail, from their abstract definition to their concrete implementation, and many points in between. The main work of the Theme One program is achieved by building and transforming a single species of graph‑theoretic data structures. In their abstract form these structures are closely related to the graphs called “cacti” and “conifers” in graph theory, so we'll generally refer to them under those names. The graph‑theoretic data structures used by the program are built up from a basic data structure called an “idea‑form flag”. That structure is defined as a pair of Pascal data types by means of the following specifications. Type Idea = ^Form • https://inquiryintoinquiry.files.wordpress.com/2022/06/theme-exposition-typ… • An “idea” is a pointer to a “form”. • A “form” is a record consisting of: • A “sign” of type char; • Four pointers, as, up, on, by, of type idea; • A “code” of type numb, that is, an integer in [0, max integer]. Represented in terms of “digraphs”, or directed graphs, the combination of an “idea” pointer and a “form” record is most easily pictured as an arc, or directed edge, leading to a node labeled with the other data, in this case, a letter and a number. At the roughest but quickest level of detail, an idea of a form can be drawn like this. Idea^Form Node • https://inquiryintoinquiry.files.wordpress.com/2022/06/theme-exposition-ide… When it is necessary to fill in more detail, the following schematic pattern can be used. Idea^Form Flag • https://inquiryintoinquiry.files.wordpress.com/2022/06/theme-exposition-ide… The idea‑form type definition determines the local structure of the whole host of graphs used by the program, including a motley array of ephemeral buffers, temporary scratch lists, and other graph‑theoretic data structures used for their transient utilities at specific points in the program. I will put off discussing these more incidental graph structures until the points where they actually arise, focusing here on the particular varieties and the specific variants of cactoid graphs making up the main formal media of the program's operation. Resources — Theme One Program • Overview • https://oeis.org/wiki/Theme_One_Program_%E2%80%A2_Overview Theme One Program • Exposition • https://oeis.org/wiki/Theme_One_Program_%E2%80%A2_Exposition Theme One Program • User Guide • https://www.academia.edu/5211369/Theme_One_Program_User_Guide Survey of Theme One Program • https://inquiryintoinquiry.com/2024/02/26/survey-of-theme-one-program-6/ Regards, Jon cc: https://www.academia.edu/community/Vv83Xj cc: https://mathstodon.xyz/@Inquiry/110039613333677509

4 months, 3 weeks

1
8
0 0

Re: [ontolog-forum] top layer ontologies, domain layer, application layer and data models

by John F Sowa

I suggest some adjustments of terminology: Mihai Nadin: In the sense [of Robert Rosen], observation is measuring. Kingsley Idehen: Observation is basically existential quantification (measurement). i.e., that something exists with certain discernible attributes. Naturally, this is situation and observer oriented. Robert Rosen (and many other philosophers, psychologists, and neuroscientists) have studied those issues in detail. Measurement is the result of comparing a percept to some standard as a result of selective attention and interpretation. What is selected depends on an open-ended variety of factors, of which situation and observer are significant. MN: The data is the outcome. The theory (based on thermodynamics) of how data is transmitted is Shannon’s contribution (with the unfortunate use of the word information as a substitute for data). The word 'data' (what is given) is inappropriate for what is observed (taken and processed by some observer). It would be a good word for what is passed along to another agent (human, animal, machine, or mythological being). Unless anybody can suggest a better word for what is stored in the brain (or computer storage), I would say that 'information' is as good as any, and better than most. Almost every word expresses it as the object of some verb. We could use the Greek word 'logos', As Heraclitus wrote and John the Evangelist repeated (about 400 years later), "In the beginning was the Logos." That word is logical. And by the way, I do not consider the word 'myth' to be a derogatory term. Some of the most fundamental truths began as myths -- and they are transmitted in the most intelligible way in a literary presentation. John __________________ From: Kingsley Idehen Hi Nadin, On 6/17/24 1:30 PM, Nadin, Mihai wrote: Measurement: the dynamics of the measured affects the dynamics of the meter (this covers from measuring devices to sensorial perception and non-sensorial evaluations). Rosen, R. 1978. Fundamentals of Measurement and representation of Natural Systems. New York :North-Holland In this sense, observation is measuring. The data is the outcome. The theory (based on thermodynamics) of how data is transmitted is Shannon’s contribution (with the unfortunate use of the word information as a substitute for data). Mihai Nadin Observation is basically existential quantification (measurement). i.e., that something exists with certain discernible attributes. Naturally, this is situation and observer oriented. Kingsley

4 months, 4 weeks

1
0
0 0

[CfP] [CoKA] : --- 2nd Call --- "Conceptual Knowledge Acquisition: Challenges, Opportunities, and Use Cases" workshop at CONCEPTS 2024

by Tom Hanika

***CoKA: --- 2nd Call for Contributions*** ================================================================ Conceptual Knowledge Acquisition: Challenges, Opportunities, and Use Cases Workshop at the 1st International Joint Conference on Conceptual Knowledge Structures (CONCEPTS 2024) September 9–13 2024, Cádiz, Spain Workshop Website: https://www.kde.cs.uni-kassel.de/coka/ Conference website: https://concepts2024.uca.es ================================================================ Formal concept analysis (FCA) can help make sense of data and the underlying domain --- provided the data is not too big, not too noisy, representative of the domain, and if there is data in the first place. What if you don’t have such data readily available but are prepared to invest in collecting it and have access to domain experts or other reliable queryable sources of information? Conceptual exploration comes to the rescue! Conceptual exploration is a family of knowledge-acquisition techniques within FCA. The goal is to build a complete implicational theory of a domain (with respect to a fixed language) by posing queries to a domain expert. When properly implemented, it is a great tool that can help organize the process of scientific discovery. Unfortunately, proper implementations are scarce and success stories of using conceptual exploration are somewhat rare and limited in scope. With this workshop, we intend to analyze the situation and, maybe, find a solution. If - you succeeded in acquiring new knowledge about or building a satisfying conceptual representation of some domain with conceptual exploration before; - you attempted conceptual exploration in application to your problem but failed miserably; - you want to use conceptual exploration to analyze some domain, but you don’t know where and how to start; - you are aware of alternatives to conceptual exploration; then come to the workshop to share your experiences, insights, ideas, and concerns with us! ================== Keywords and Topics ================== Knowledge Acquisition and Capture Conceptual Exploration Design Patterns and Paradigmatic Examples successful use cases and real-world applications challenges and lessons learned application principles missing theoretical foundations missing technical infrastructure integration with other theories and technologies ========================= Duration, Format, and Dates ========================= We invite contributions in the form of an extended abstract of up to two pages. In addition, supplementary material, such as data sets, detailed descriptions, or visualizations, may be submitted. The workshop is planned for half a day within the conference dates and at the same venue. It will consist of several short presentations each followed by a plenary discussion. Please send your contributions until *July 10, 2024* to tom.hanika(a)uni-hildesheim.de. If you are not sure whether your contribution matches the topics or the format of the workshop, you are welcome to contact the organizers prior to submitting the abstract. An acceptance notification will be sent within two weeks upon receiving the submission. =================== Workshop Organizers =================== - Tom Hanika, University of Hildesheim - Sergei Obiedkov, TU Dresden - Bernhard Ganter, Ernst-Schröder-Zentrum, Darmstadt

4 months, 4 weeks

1
0
0 0

2024

2023

2022

2021

CG June 2024