Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.lang.prolog > #15477

LRM moving from FOM to TCS [Lean Prover] (Was: Is Causal AI simply ReLU (Geoffrey E. Hinton 2010)))

From Mild Shock <janburse@fastmail.fm>
Newsgroups comp.lang.prolog
Subject LRM moving from FOM to TCS [Lean Prover] (Was: Is Causal AI simply ReLU (Geoffrey E. Hinton 2010)))
Date 2026-02-27 10:20 +0100
Message-ID <10nrnlo$ssl0$1@solani.org> (permalink)
References (7 earlier) <vig8n2$847h$3@solani.org> <10lu6t9$7pg1$1@solani.org> <10mpd71$5kp7$1@solani.org> <10mpnk6$6ciu$2@solani.org> <10n1gdd$avob$1@solani.org>

Show all headers | View raw

Hi,

Large Reasoning Models (LRM) seem to move from
Foundation of Mathematics (FOM) to Theoretical
Computer Science (TCS). FOM typically gives

you "white science" mathematics, with sets and
infinity, if you are lucky a little recursion
theory. Fun fact TCS is even more "white".

Interesting paper in as far:

Lean Meets Theoretical Computer Science:
Scalable Synthesis of Theorem Proving Challenges
in Formal-Informal Pairs
Terry Jingchen Zhang et. al. - 2025
https://arxiv.org/abs/2508.15878v1

One swallow does not make a summer?

But its probably a necessary step. The above
paper using Busy Beaver and Interger Constraints
as examples. What logical frameworks do even

apply, is it enough to have a "total function"
theory layer, or does TCS need more. TCS can
be heavy on all sort of discrete and

non-discrete mathematics.

Bye

Mild Shock schrieb:
> Hi,
> 
> Geoffrey E. Hinton, the Nobel Prize winner
> for AI. He was already beating the drums
> for ReLU in 2010:
> 
> HRectified Linear Units Improve Restricted Boltzmann Machines
> Geoffrey E. Hinton & Vinod Nair - 2010
> https://www.cs.toronto.edu/~fritz/absps/reluICML.pdf
> 
> Because ANNs (Artificial Neural Networks) were originally
> designed with other functions, e.g. with Logistic function:
> 
> An artificial neuron is a mathematical function conceived
> as a model of a biological neuron in a neural network.
> https://en.wikipedia.org/wiki/Artificial_neuron
> 
> If you populate additive factor graphs with log P,
> you basically get multiplicative factor graphs.
> So an ANN can express belief networks, right?
> 
> Bye
> 
> P.S.: What is all the hype about Causal AI, and
> the Ladder of Causation à la Judea Pearl?
> 
> Causal AI – the next gen AI
> Prof. Sotirios A. Tsaftaris - 2025
> https://www.youtube.com/watch?v=IelslFzdsYw

Back to comp.lang.prolog | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-06-04 07:49 -0700
  Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-06-20 08:20 -0700
    Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-06-21 03:24 -0700
    Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-06-23 02:14 -0700
      Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-06-24 15:25 -0700
        Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-07-29 17:58 -0700
          Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-08-01 06:48 -0700
            Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-08-01 06:54 -0700
              Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-08-01 07:31 -0700
                Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-08-02 02:02 -0700
                Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-08-02 02:14 -0700
                Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-08-02 02:20 -0700
                Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-08-15 07:34 -0700
      Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-20 05:23 -0800
        Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-20 09:01 -0800
          Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-25 07:23 -0800
            Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-25 13:10 -0800
              Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-27 09:31 -0800
                Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-28 21:47 -0800
                Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-28 21:58 -0800
                Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-28 23:33 -0800
                Re: The road to Artificial Intelligence Mild Shock <bursejan@gmail.com> - 2023-11-30 15:43 -0800
      Zero Tokens comming out of me (Re: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-10-30 16:47 +0100
    FYI: New Journal NAI (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-11-06 17:18 +0100
      The Bee Clock Model (Re: FYI: New Journal NAI) Mild Shock <janburse@fastmail.fm> - 2024-11-06 17:41 +0100
    ChatGPT for the Flintstones: Bloomberg (Re: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-11-11 22:34 +0100
      Silicon Valley is the new Detroit (Re: ChatGPT for the Flintstones: Bloomberg) Mild Shock <janburse@fastmail.fm> - 2025-02-18 18:13 +0100
        Re: Silicon Valley is the new Detroit (Re: ChatGPT for the Flintstones: Bloomberg) Mild Shock <janburse@fastmail.fm> - 2025-02-18 18:14 +0100
  Minimal Logics in the 2020's: A Meteoric Rise (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-07-04 23:09 +0200
    The curse of Negri & Plato (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-05 03:52 +0200
      Re: The curse of Negri & Plato (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-05 03:54 +0200
        Euklid: Am I a joke to you? (Re: The curse of Negri & Plato) Mild Shock <janburse@fastmail.fm> - 2024-07-13 08:21 +0200
    Re: Minimal Logics in the 2020's: A Meteoric Rise (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-07-05 06:38 +0200
      Re: Minimal Logics in the 2020's: A Meteoric Rise (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-07-07 23:13 +0200
        Re: Minimal Logics in the 2020's: A Meteoric Rise (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-07-07 23:17 +0200
    French Philosophy in 2024 (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-12 11:27 +0200
      Re: French Philosophy in 2024 (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-12 11:37 +0200
        Corona isn't over 2024 (Was: French Philosophy in 2024) Mild Shock <janburse@fastmail.fm> - 2024-07-12 12:20 +0200
        Re: Corona isn't over 2024 (Was: French Philosophy in 2024) Mild Shock <janburse@fastmail.fm> - 2024-07-12 12:36 +0200
    The error in Jan von Platos presentation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-13 10:33 +0200
      Re: The error in Jan von Platos presentation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-13 10:58 +0200
        Re: The error in Jan von Platos presentation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-14 00:05 +0200
          Re: The error in Jan von Platos presentation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-14 00:14 +0200
    Distinction between Computation & Derivation (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-22 12:55 +0200
    Prolegomena by Rappaport (Re: Minimal Logics in the 2020's: A Meteoric Rise (Was: The road to Artificial Intelligence)) Mild Shock <janburse@fastmail.fm> - 2024-07-31 22:15 +0200
      2nd Cognitive Turn ~~> no Bayesian Brain (Re: Prolegomena by Rappaport) Mild Shock <janburse@fastmail.fm> - 2024-08-03 22:50 +0200
        Ok I made a joke, sorry (e: 2nd Cognitive Turn ~~> no Bayesian Brain) Mild Shock <janburse@fastmail.fm> - 2024-08-03 23:29 +0200
          Re: Ok I made a joke, sorry (e: 2nd Cognitive Turn ~~> no Bayesian Brain) Mild Shock <janburse@fastmail.fm> - 2024-08-03 23:55 +0200
            bullshit bullshit bullshit (Re: Ok I made a joke, sorry) Mild Shock <janburse@fastmail.fm> - 2024-08-04 00:14 +0200
    The two rules (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-08-04 00:57 +0200
    "Emotional AI" and "Spiritual AI" (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-10-03 12:28 +0200
      Oh shit, too late! (Re: "Emotional AI" and "Spiritual AI" (Re: Minimal Logics in the 2020's: A Meteoric Rise)) Mild Shock <janburse@fastmail.fm> - 2024-10-03 12:40 +0200
  LLM and Prolog, a Marriage in Heaven? (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-08-04 22:10 +0200
    The anchoring problem in a real world philosopher (Was: LLM and Prolog, a Marriage in Heaven?) Mild Shock <janburse@fastmail.fm> - 2024-08-08 16:56 +0200
      Long life learning also for real world philosophers? (Re: The anchoring problem in a real world philosopher) Mild Shock <janburse@fastmail.fm> - 2024-08-08 17:18 +0200
  Prolog for the pre frontal context (PFC) (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-08-28 17:28 +0200
  Re: Prolog for the pre frontal cortex (PFC) (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-08-28 17:31 +0200
  No time for the hairdresser betweeen 09.06.2023 and 11.07.2024 (Re: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-09-01 16:43 +0200
  Holy Shit: AI is cheaper than Humans (Was: The road to Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-09-01 22:38 +0200
    AI robots from Disney (Was: Holy Shit: AI is cheaper than Humans) Mild Shock <janburse@fastmail.fm> - 2024-09-01 23:17 +0200
      I can't stand Mira Murati's Eyewash (Was: AI robots from Disney (Was: Holy Shit: AI is cheaper than Humans)) Mild Shock <janburse@fastmail.fm> - 2024-09-03 12:01 +0200
        After blue, green why not start yellow (Re: I can't stand Mira Murati's Eyewash) Mild Shock <janburse@fastmail.fm> - 2024-09-03 17:56 +0200
          miramurati bye bye (Re: After blue, green why not start yellow) Mild Shock <janburse@fastmail.fm> - 2024-09-25 22:09 +0200
            Im memoriam Doug Lenant (1950 - 2023) (Re: miramurati bye bye) Mild Shock <janburse@fastmail.fm> - 2024-12-01 00:56 +0100
              2026 the Year Prolog **plonked** Itself [Strawberry Prolog is back] (Was: Im memoriam Doug Lenant (1950 - 2023)) Mild Shock <janburse@fastmail.fm> - 2026-02-04 02:20 +0100
                Spies and Playboys: Don't use insecure E-mail [https://www.jmail.world/ Example] Mild Shock <janburse@fastmail.fm> - 2026-02-04 11:19 +0100
                Some ANTHEM Cringe Nonsense [More Dead Horses] (Was: 2026 the Year Prolog **plonked** Itself [Strawberry Prolog is back]) Mild Shock <janburse@fastmail.fm> - 2026-02-05 09:53 +0100
                Gecode: Guns N' Roses - Dead Horse (Was: Some ANTHEM Cringe Nonsense [More Dead Horses]) Mild Shock <janburse@fastmail.fm> - 2026-02-05 10:21 +0100
                2026 the Year golang lost its Marbles (Was: 2026 the Year Prolog **plonked** Itself [Strawberry Prolog is back]) Mild Shock <janburse@fastmail.fm> - 2026-02-14 09:53 +0100
                Mark V. Shaney caused Julio Di Egidio Suicide (Re: 2026 the Year golang lost its Marble) Mild Shock <janburse@fastmail.fm> - 2026-02-14 12:51 +0100
                Is Causal AI simply ReLU (Geoffrey E. Hinton 2010) (Re: Mark V. Shaney caused Julio Di Egidio Suicide) Mild Shock <janburse@fastmail.fm> - 2026-02-17 11:37 +0100
                Gen Alpha will grow up with Causal AI (Was: Is Causal AI simply ReLU (Geoffrey E. Hinton 2010)) Mild Shock <janburse@fastmail.fm> - 2026-02-19 20:00 +0100
                LRM moving from FOM to TCS [Lean Prover] (Was: Is Causal AI simply ReLU (Geoffrey E. Hinton 2010))) Mild Shock <janburse@fastmail.fm> - 2026-02-27 10:20 +0100
                Original Subject established by Chinese Scientists [Extenics] (Re: LRM moving from FOM to TCS [Lean Prover]) Mild Shock <janburse@fastmail.fm> - 2026-02-28 16:36 +0100
                DeepSeekMath: From psychophysischer Parallelismus to GPRO (Re: Odysseus PTSD: Does Function need Consistency?) Mild Shock <janburse@fastmail.fm> - 2026-03-06 02:29 +0100
            "superhumaness" excels "stackoverflow reputation" (Was: Im memoriam Doug Lenant (1950 - 2023) Mild Shock <janburse@fastmail.fm> - 2024-12-01 01:08 +0100
              para-governemental institution of violence (Re: "superhumaness" excels "stackoverflow reputation") Mild Shock <janburse@fastmail.fm> - 2024-12-01 11:42 +0100
              Not only $TSLA is on fire sale! [The Decline of Prolog] (Was: "superhumaness" excels "stackoverflow reputation") Mild Shock <janburse@fastmail.fm> - 2025-03-14 13:37 +0100
                Re: Not only $TSLA is on fire sale! [The Decline of Prolog] (Was: "superhumaness" excels "stackoverflow reputation") Mild Shock <janburse@fastmail.fm> - 2025-03-14 14:06 +0100
                Splitting up the Prologue to Prolog Mild Shock <janburse@fastmail.fm> - 2025-05-19 10:54 +0200
    Safe Superintelligence (SSI): Now they are dancing Mild Shock <janburse@fastmail.fm> - 2024-09-05 19:51 +0200
      Re: Safe Superintelligence (SSI): Now they are dancing Mild Shock <janburse@fastmail.fm> - 2024-09-05 23:51 +0200
        Salem Aleikum: Maxwella's Equations Mild Shock <janburse@fastmail.fm> - 2024-09-09 13:15 +0200
          non judicium, sed latrocinium (Re: Salem Aleikum: Maxwella's Equations) Mild Shock <janburse@fastmail.fm> - 2024-09-10 08:58 +0200
        Internet was made for cats (Re: Safe Superintelligence (SSI): Now they are dancing) Mild Shock <janburse@fastmail.fm> - 2024-09-13 12:58 +0200
          I was there, 3000 years ago (Re: Internet was made for cats) Mild Shock <janburse@fastmail.fm> - 2024-09-13 13:01 +0200
            Even Haitians are now voting for Trump (Re: I was there, 3000 years ago (Re: Internet was made for cats)) Mild Shock <janburse@fastmail.fm> - 2024-09-13 13:04 +0200
          supply chain attack (Was: Internet was made for cats( Mild Shock <janburse@fastmail.fm> - 2024-09-17 22:18 +0200
            Polyfill Supply Chain Attack (Was: supply chain attack) Mild Shock <janburse@fastmail.fm> - 2024-10-11 09:12 +0200
    USA is shitting its pants (Was: Holy Shit: AI is cheaper than Humans) Mild Shock <janburse@fastmail.fm> - 2024-09-16 00:20 +0200
      scryer prolog is dead, BILAI instead? (Was: USA is shitting its pants) Mild Shock <janburse@fastmail.fm> - 2024-09-18 15:45 +0200
        Microsoft is plagiarizing my Invention [LLMs under the hood] Mild Shock <janburse@fastmail.fm> - 2024-10-08 16:00 +0200
          Geoffrey Hinton / Nobelpreis für Physik [Re: Microsoft is plagiarizing my Invention [LLMs under the hood]] Mild Shock <janburse@fastmail.fm> - 2024-10-08 16:03 +0200
        thank you for the FLOPs (Was: scryer prolog is dead, BILAI instead?) Mild Shock <janburse@fastmail.fm> - 2024-12-01 14:34 +0100
          Is old school mode directed compilation dead? (Was: thank you for the FLOPs) Mild Shock <janburse@fastmail.fm> - 2025-01-24 17:57 +0100
            Re: Is old school mode directed compilation dead? (Was: thank you for the FLOPs) Mild Shock <janburse@fastmail.fm> - 2025-01-24 17:58 +0100
              format/2 doesn't agree with Trealla or SWI (Was: Is old school mode directed compilation dead?) Mild Shock <janburse@fastmail.fm> - 2025-01-25 14:13 +0100
              DCG Translation with Unification Spillling (Was: Is old school mode directed compilation dead?) Mild Shock <janburse@fastmail.fm> - 2025-01-25 20:44 +0100
                Re: DCG Translation with Unification Spillling (Was: Is old school mode directed compilation dead?) Mild Shock <janburse@fastmail.fm> - 2025-01-25 20:44 +0100
          Will WASM be fast some time? (Was: thank you for the FLOPs) Mild Shock <janburse@fastmail.fm> - 2025-03-04 10:09 +0100
            Re: Will WASM be fast some time? (Was: thank you for the FLOPs) Mild Shock <janburse@fastmail.fm> - 2025-03-04 10:13 +0100
      Book Project: WomanLogic (Re: USA is shitting its pants) Mild Shock <janburse@fastmail.fm> - 2024-11-14 22:25 +0100
        Re: Book Project: WomanLogic (Re: USA is shitting its pants) Mild Shock <janburse@fastmail.fm> - 2024-11-14 22:26 +0100
  Happy Birthday 75 Years of Artificial Intelligence Mild Shock <janburse@fastmail.fm> - 2024-10-23 01:18 +0200
    Does ChatGPT know the difference between "k" and "kkkkkkkkkk"? Mild Shock <janburse@fastmail.fm> - 2024-10-23 01:18 +0200
    What is it like to be a Bat? Mild Shock <janburse@fastmail.fm> - 2024-10-23 22:35 +0200
      How Monkeys see the World (Re: What is it like to be a Bat?) Mild Shock <janburse@fastmail.fm> - 2024-10-23 22:45 +0200
    Low-Code Penetration Prediction (Re: Happy Birthday 75 Years of Artificial Intelligence) Mild Shock <janburse@fastmail.fm> - 2024-10-30 23:09 +0100

csiph-web