Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.theory > #25729 > unrolled thread
| Started by | "dklei...@gmail.com" <dkleinecke@gmail.com> |
|---|---|
| First post | 2020-11-23 11:37 -0800 |
| Last post | 2020-11-24 03:59 +0000 |
| Articles | 20 on this page of 45 — 7 participants |
Back to article view | Back to comp.theory
Not about Olcutt "dklei...@gmail.com" <dkleinecke@gmail.com> - 2020-11-23 11:37 -0800
Re: Not about Olcutt olcott <NoOne@NoWhere.com> - 2020-11-23 13:46 -0600
Re: Not about Olcutt Richard Damon <Richard@Damon-Family.org> - 2020-11-23 15:04 -0500
Re: Not about Olcutt Jeff Barnett <jbb@notatt.com> - 2020-11-23 15:52 -0700
Re: Not about Olcutt Richard Damon <Richard@Damon-Family.org> - 2020-11-23 18:08 -0500
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-23 17:35 -0600
Re: Not about Olcutt Andy Walker <anw@cuboid.co.uk> - 2020-11-24 10:36 +0000
Re: Not about Olcutt Malcolm McLean <malcolm.arthur.mclean@gmail.com> - 2020-11-23 13:06 -0800
Re: Not about Olcutt "dklei...@gmail.com" <dkleinecke@gmail.com> - 2020-11-23 13:51 -0800
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-23 15:55 -0600
Re: Church-Turing thesis Jeff Barnett <jbb@notatt.com> - 2020-11-23 16:16 -0700
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-23 17:34 -0600
Re: Church-Turing thesis Richard Damon <Richard@Damon-Family.org> - 2020-11-23 19:51 -0500
Re: Church-Turing thesis Jeff Barnett <jbb@notatt.com> - 2020-11-23 18:10 -0700
Re: Church-Turing thesis Jeff Barnett <jbb@notatt.com> - 2020-11-24 14:11 -0700
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 15:40 -0600
Re: Church-Turing thesis Malcolm McLean <malcolm.arthur.mclean@gmail.com> - 2020-11-24 15:12 -0800
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 17:28 -0600
Re: Church-Turing thesis Richard Damon <Richard@Damon-Family.org> - 2020-11-24 18:43 -0500
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 18:05 -0600
Re: Church-Turing thesis Ben Bacarisse <ben.usenet@bsb.me.uk> - 2020-11-25 03:30 +0000
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 21:43 -0600
Re: Church-Turing thesis Ben Bacarisse <ben.usenet@bsb.me.uk> - 2020-11-25 21:25 +0000
Re: Church-Turing thesis Jeff Barnett <jbb@notatt.com> - 2020-11-24 16:26 -0700
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 17:33 -0600
Re: Church-Turing thesis Richard Damon <Richard@Damon-Family.org> - 2020-11-24 18:38 -0500
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 17:44 -0600
Re: Church-Turing thesis Jeff Barnett <jbb@notatt.com> - 2020-11-24 16:19 -0700
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 17:26 -0600
Re: Church-Turing thesis Jeff Barnett <jbb@notatt.com> - 2020-11-24 18:12 -0700
Re: Church-Turing thesis Ben Bacarisse <ben.usenet@bsb.me.uk> - 2020-11-25 03:33 +0000
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 21:47 -0600
Re: Church-Turing thesis Ben Bacarisse <ben.usenet@bsb.me.uk> - 2020-11-24 23:23 +0000
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 17:31 -0600
Re: Church-Turing thesis Jeff Barnett <jbb@notatt.com> - 2020-11-24 18:14 -0700
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-24 19:37 -0600
Re: Church-Turing thesis Jeff Barnett <jbb@notatt.com> - 2020-11-25 11:49 -0700
Re: Church-Turing thesis Ben Bacarisse <ben.usenet@bsb.me.uk> - 2020-11-25 21:30 +0000
Re: Not about Olcutt Richard Damon <Richard@Damon-Family.org> - 2020-11-23 17:02 -0500
Re: Not about Olcutt Jeff Barnett <jbb@notatt.com> - 2020-11-23 15:56 -0700
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-23 17:36 -0600
Re: Not about Olcutt Jeff Barnett <jbb@notatt.com> - 2020-11-23 15:54 -0700
Re: Not about Olcutt Ben Bacarisse <ben.usenet@bsb.me.uk> - 2020-11-24 02:00 +0000
Re: Church-Turing thesis olcott <NoOne@NoWhere.com> - 2020-11-23 20:12 -0600
Re: Church-Turing thesis Ben Bacarisse <ben.usenet@bsb.me.uk> - 2020-11-24 03:59 +0000
Page 2 of 3 — ← Prev page 1 [2] 3 Next page →
| From | Ben Bacarisse <ben.usenet@bsb.me.uk> |
|---|---|
| Date | 2020-11-25 03:30 +0000 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <877dqa865l.fsf@bsb.me.uk> |
| In reply to | #25848 |
olcott <NoOne@NoWhere.com> writes: > On 11/24/2020 5:12 PM, Malcolm McLean wrote: >> On Tuesday, 24 November 2020 at 21:42:22 UTC, olcott wrote: >>> On 11/24/2020 3:11 PM, Jeff Barnett wrote: >>>> On 11/23/2020 4:34 PM, olcott wrote: >>>>> >>>>> A UTM is the only form of a self-modfying Turing machine that I could >>>>> think of. A data driven machine could accomplish the same thing by >>>>> modifying its data. >>>> >>>> A UTM IS NOT A SELF MODIFYING TOURING MACHINE. >>> That is not what I said. You can't even manage to get my words right. >>> Self modification is a very powerful computing concept. >>> >> A Turing machine has no way of modifying its state table. > > However a UTM can modify is TMD of itself, thus become self-modfying. A UTM does not usually use an encoding of itself -- it uses the encoding of another machine. Of course, a UTM can be given an input that is its own encoding, but even if it were to alter that during execution (whilst still somehow doing what a UTM must do), it is still not /self/ modifying. -- Ben.
[toc] | [prev] | [next] | [standalone]
| From | olcott <NoOne@NoWhere.com> |
|---|---|
| Date | 2020-11-24 21:43 -0600 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <7KKdnQOnCv1yTyDCnZ2dnUU7-d3NnZ2d@giganews.com> |
| In reply to | #25892 |
On 11/24/2020 9:30 PM, Ben Bacarisse wrote: > olcott <NoOne@NoWhere.com> writes: > >> On 11/24/2020 5:12 PM, Malcolm McLean wrote: >>> On Tuesday, 24 November 2020 at 21:42:22 UTC, olcott wrote: >>>> On 11/24/2020 3:11 PM, Jeff Barnett wrote: >>>>> On 11/23/2020 4:34 PM, olcott wrote: >>>>>> >>>>>> A UTM is the only form of a self-modfying Turing machine that I could >>>>>> think of. A data driven machine could accomplish the same thing by >>>>>> modifying its data. >>>>> >>>>> A UTM IS NOT A SELF MODIFYING TOURING MACHINE. >>>> That is not what I said. You can't even manage to get my words right. >>>> Self modification is a very powerful computing concept. >>>> >>> A Turing machine has no way of modifying its state table. >> >> However a UTM can modify is TMD of itself, thus become self-modfying. > > A UTM does not usually use an encoding of itself -- it uses the encoding > of another machine. Of course, a UTM can be given an input that is its > own encoding, but even if it were to alter that during execution (whilst > still somehow doing what a UTM must do), it is still not /self/ > modifying. > If a master UTM was executing the current UTM's TMD and this same simulated UTM was provided with the place on the master UTM tape where it itself is located then modifing these tape locations would be modifying its actual self. -- Copyright 2020 Pete Olcott "Great spirits have always encountered violent opposition from mediocre minds." Einstein
[toc] | [prev] | [next] | [standalone]
| From | Ben Bacarisse <ben.usenet@bsb.me.uk> |
|---|---|
| Date | 2020-11-25 21:25 +0000 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <87eekh6sdk.fsf@bsb.me.uk> |
| In reply to | #25900 |
olcott <NoOne@NoWhere.com> writes: > On 11/24/2020 9:30 PM, Ben Bacarisse wrote: >> olcott <NoOne@NoWhere.com> writes: >> >>> On 11/24/2020 5:12 PM, Malcolm McLean wrote: >>>> On Tuesday, 24 November 2020 at 21:42:22 UTC, olcott wrote: >>>>> On 11/24/2020 3:11 PM, Jeff Barnett wrote: >>>>>> On 11/23/2020 4:34 PM, olcott wrote: >>>>>>> >>>>>>> A UTM is the only form of a self-modfying Turing machine that I could >>>>>>> think of. A data driven machine could accomplish the same thing by >>>>>>> modifying its data. >>>>>> >>>>>> A UTM IS NOT A SELF MODIFYING TOURING MACHINE. >>>>> That is not what I said. You can't even manage to get my words right. >>>>> Self modification is a very powerful computing concept. >>>>> >>>> A Turing machine has no way of modifying its state table. >>> >>> However a UTM can modify is TMD of itself, thus become self-modfying. >> >> A UTM does not usually use an encoding of itself -- it uses the encoding >> of another machine. Of course, a UTM can be given an input that is its >> own encoding, but even if it were to alter that during execution (whilst >> still somehow doing what a UTM must do), it is still not /self/ >> modifying. >> > If a master UTM was executing the current UTM's TMD and this same > simulated UTM was provided with the place on the master UTM tape where > it itself is located then modifing these tape locations would be > modifying its actual self. No. Your scenario includes only one TM and it remain unmodified throughout. -- Ben.
[toc] | [prev] | [next] | [standalone]
| From | Jeff Barnett <jbb@notatt.com> |
|---|---|
| Date | 2020-11-24 16:26 -0700 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <rpk4qp$ven$1@dont-email.me> |
| In reply to | #25837 |
On 11/24/2020 2:40 PM, olcott wrote: > On 11/24/2020 3:11 PM, Jeff Barnett wrote: >> On 11/23/2020 4:34 PM, olcott wrote: >>> On 11/23/2020 5:16 PM, Jeff Barnett wrote: >>>> On 11/23/2020 2:55 PM, olcott wrote: >>>>> On 11/23/2020 3:51 PM, dklei...@gmail.com wrote: >>>>>> On Monday, November 23, 2020 at 1:06:29 PM UTC-8, >>>>>> malcolm.ar...@gmail.com wrote: >>>>>>> On Monday, 23 November 2020 at 19:37:13 UTC, dklei...@gmail.com >>>>>>> wrote: >>>>>>>> I hope that comp.theory is the best place for the following >>>>>>>> question: >>>>>>>> >>>>>>>> Has it ever been shown that a Turing Machine can do the >>>>>>>> kind of neural network calculating done by AI such as Siri? >>>>>>>> >>>>>>>> This in the context of whether or not such calculating can >>>>>>>> legitimately be called algorithmic. It is not algorithmic in >>>>>>>> sense Knuth uses the word "algorithm". >>>>>>>> >>>>>>> "Neural network" was a great marketing term. But all a neural >>>>>>> network is is a directed graph, weights, and a sigmoid function to >>>>>>> prevent high weights pushing output very high and to make the >>>>>>> results continously differentiable to help out the training >>>>>>> algorithm. >>>>>>> >>>>>>> It doesn't emulate a real human brain. >>>>>> >>>>>> The problem here is that the neural networks continually modify the >>>>>> network and a Turing Machine can't be modified on the fly. >>>>> >>>>> Sure it can. A UTM can simulate its own TDM and modify this TMD at >>>>> any point in time. Basically anything that a computer can do some >>>>> TM can do. >>>>> >>>>>> Can we >>>>>> use a Turing Machine to simulate another mode of calculating >>>>>> (neural nets) and still say that Turing Machine is doing the >>>>>> processing. >>>>>> That is, assuming a Turing Machine can simulate a neural net. The >>>>>> Church-Turing thesis is not a theorem - how sure of it are we? >>>> This reply shows how little you know about the subject. Why on earth >>>> is a UTM needed for this task? It isn't. In fact it adds complexity >>>> and no additional transparency or ease of programming. Stick to your >>>> own stupid threads. This one is named "Not about Olcott" in an >>>> effort to avoid that stupidity. Your lack of knowledge, arrogance, >>>> and misuse of terminology gives threads the odor of poop. Please >>>> return to your studies. You have not yet achieved novice status nor >>>> are considered an earnest performer; just a misguided lost soul. >>>> Give it a rest. >>> >>> A UTM is the only form of a self-modfying Turing machine that I could >>> think of. A data driven machine could accomplish the same thing by >>> modifying its data. >> >> A UTM IS NOT A SELF MODIFYING TOURING MACHINE. > > That is not what I said. You can't even manage to get my words right. > Self modification is a very powerful computing concept. Moron Look up a few lines where you say "A UTM is the only form of a self-modfying Turing machine that I could think of." Do you recognize it? Do you remember writing it or was your habd in your pants again? Do you see why the debate in the newsgroup is not really about you claims, rather we are probing to find out your dominate character: is you a moron or an ignoramus? The smart money is on both. -- Jeff Barnett
[toc] | [prev] | [next] | [standalone]
| From | olcott <NoOne@NoWhere.com> |
|---|---|
| Date | 2020-11-24 17:33 -0600 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <e82dnXSkCo7PBSDCnZ2dnUU7-RlQAAAA@giganews.com> |
| In reply to | #25846 |
On 11/24/2020 5:26 PM, Jeff Barnett wrote: > On 11/24/2020 2:40 PM, olcott wrote: >> On 11/24/2020 3:11 PM, Jeff Barnett wrote: >>> On 11/23/2020 4:34 PM, olcott wrote: >>>> On 11/23/2020 5:16 PM, Jeff Barnett wrote: >>>>> On 11/23/2020 2:55 PM, olcott wrote: >>>>>> On 11/23/2020 3:51 PM, dklei...@gmail.com wrote: >>>>>>> On Monday, November 23, 2020 at 1:06:29 PM UTC-8, >>>>>>> malcolm.ar...@gmail.com wrote: >>>>>>>> On Monday, 23 November 2020 at 19:37:13 UTC, dklei...@gmail.com >>>>>>>> wrote: >>>>>>>>> I hope that comp.theory is the best place for the following >>>>>>>>> question: >>>>>>>>> >>>>>>>>> Has it ever been shown that a Turing Machine can do the >>>>>>>>> kind of neural network calculating done by AI such as Siri? >>>>>>>>> >>>>>>>>> This in the context of whether or not such calculating can >>>>>>>>> legitimately be called algorithmic. It is not algorithmic in >>>>>>>>> sense Knuth uses the word "algorithm". >>>>>>>>> >>>>>>>> "Neural network" was a great marketing term. But all a neural >>>>>>>> network is is a directed graph, weights, and a sigmoid function to >>>>>>>> prevent high weights pushing output very high and to make the >>>>>>>> results continously differentiable to help out the training >>>>>>>> algorithm. >>>>>>>> >>>>>>>> It doesn't emulate a real human brain. >>>>>>> >>>>>>> The problem here is that the neural networks continually modify the >>>>>>> network and a Turing Machine can't be modified on the fly. >>>>>> >>>>>> Sure it can. A UTM can simulate its own TDM and modify this TMD at >>>>>> any point in time. Basically anything that a computer can do some >>>>>> TM can do. >>>>>> >>>>>>> Can we >>>>>>> use a Turing Machine to simulate another mode of calculating >>>>>>> (neural nets) and still say that Turing Machine is doing the >>>>>>> processing. >>>>>>> That is, assuming a Turing Machine can simulate a neural net. The >>>>>>> Church-Turing thesis is not a theorem - how sure of it are we? >>>>> This reply shows how little you know about the subject. Why on >>>>> earth is a UTM needed for this task? It isn't. In fact it adds >>>>> complexity and no additional transparency or ease of programming. >>>>> Stick to your own stupid threads. This one is named "Not about >>>>> Olcott" in an effort to avoid that stupidity. Your lack of >>>>> knowledge, arrogance, and misuse of terminology gives threads the >>>>> odor of poop. Please return to your studies. You have not yet >>>>> achieved novice status nor are considered an earnest performer; >>>>> just a misguided lost soul. Give it a rest. >>>> >>>> A UTM is the only form of a self-modfying Turing machine that I >>>> could think of. A data driven machine could accomplish the same >>>> thing by modifying its data. >>> >>> A UTM IS NOT A SELF MODIFYING TOURING MACHINE. >> >> That is not what I said. You can't even manage to get my words right. >> Self modification is a very powerful computing concept. > > Moron Look up a few lines where you say "A UTM is the only form of a > self-modfying Turing machine that I could think of." Yes I realized that after posting it because I was referring this this: >>>>>> A UTM can simulate its own TDM and modify this TMD at >>>>>> any point in time. Basically anything that a computer can do some >>>>>> TM can do. > Do you recognize > it? Do you remember writing it or was your habd in your pants again? Do > you see why the debate in the newsgroup is not really about you claims, > rather we are probing to find out your dominate character: is you a > moron or an ignoramus? The smart money is on both. -- Copyright 2020 Pete Olcott "Great spirits have always encountered violent opposition from mediocre minds." Einstein
[toc] | [prev] | [next] | [standalone]
| From | Richard Damon <Richard@Damon-Family.org> |
|---|---|
| Date | 2020-11-24 18:38 -0500 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <zPgvH.27759$Uz.6274@fx46.iad> |
| In reply to | #25837 |
On 11/24/20 4:40 PM, olcott wrote: > On 11/24/2020 3:11 PM, Jeff Barnett wrote: >> On 11/23/2020 4:34 PM, olcott wrote: >>> A UTM is the only form of a self-modfying Turing machine that I could >>> think of. A data driven machine could accomplish the same thing by >>> modifying its data. >> >> A UTM IS NOT A SELF MODIFYING TOURING MACHINE. > > That is not what I said. You can't even manage to get my words right. > Self modification is a very powerful computing concept. > > Jee Peter, it sure looks like that is what you said.
[toc] | [prev] | [next] | [standalone]
| From | olcott <NoOne@NoWhere.com> |
|---|---|
| Date | 2020-11-24 17:44 -0600 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <8JmdnV2nC_ROByDCnZ2dnUU7-W2dnZ2d@giganews.com> |
| In reply to | #25853 |
On 11/24/2020 5:38 PM, Richard Damon wrote: > On 11/24/20 4:40 PM, olcott wrote: >> On 11/24/2020 3:11 PM, Jeff Barnett wrote: >>> On 11/23/2020 4:34 PM, olcott wrote: > >>>> A UTM is the only form of a self-modfying Turing machine that I could >>>> think of. A data driven machine could accomplish the same thing by >>>> modifying its data. >>> >>> A UTM IS NOT A SELF MODIFYING TOURING MACHINE. >> >> That is not what I said. You can't even manage to get my words right. >> Self modification is a very powerful computing concept. >> >> > > Jee Peter, it sure looks like that is what you said. > My mistake, yet I was referring to what I said originally: On 11/23/2020 3:55 PM, olcott wrote: Sure it can. A UTM can simulate its own TDM and modify this TMD at any point in time. Basically anything that a computer can do some TM can do -- Copyright 2020 Pete Olcott "Great spirits have always encountered violent opposition from mediocre minds." Einstein
[toc] | [prev] | [next] | [standalone]
| From | Jeff Barnett <jbb@notatt.com> |
|---|---|
| Date | 2020-11-24 16:19 -0700 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <rpk4eu$tao$1@dont-email.me> |
| In reply to | #25757 |
On 11/23/2020 4:34 PM, olcott wrote: > On 11/23/2020 5:16 PM, Jeff Barnett wrote: >> On 11/23/2020 2:55 PM, olcott wrote: >>> On 11/23/2020 3:51 PM, dklei...@gmail.com wrote: >>>> On Monday, November 23, 2020 at 1:06:29 PM UTC-8, >>>> malcolm.ar...@gmail.com wrote: >>>>> On Monday, 23 November 2020 at 19:37:13 UTC, dklei...@gmail.com wrote: >>>>>> I hope that comp.theory is the best place for the following >>>>>> question: >>>>>> >>>>>> Has it ever been shown that a Turing Machine can do the >>>>>> kind of neural network calculating done by AI such as Siri? >>>>>> >>>>>> This in the context of whether or not such calculating can >>>>>> legitimately be called algorithmic. It is not algorithmic in >>>>>> sense Knuth uses the word "algorithm". >>>>>> >>>>> "Neural network" was a great marketing term. But all a neural >>>>> network is is a directed graph, weights, and a sigmoid function to >>>>> prevent high weights pushing output very high and to make the >>>>> results continously differentiable to help out the training algorithm. >>>>> >>>>> It doesn't emulate a real human brain. >>>> >>>> The problem here is that the neural networks continually modify the >>>> network and a Turing Machine can't be modified on the fly. >>> >>> Sure it can. A UTM can simulate its own TDM and modify this TMD at >>> any point in time. Basically anything that a computer can do some TM >>> can do. >>> >>>> Can we >>>> use a Turing Machine to simulate another mode of calculating >>>> (neural nets) and still say that Turing Machine is doing the >>>> processing. >>>> That is, assuming a Turing Machine can simulate a neural net. The >>>> Church-Turing thesis is not a theorem - how sure of it are we? >> This reply shows how little you know about the subject. Why on earth >> is a UTM needed for this task? It isn't. In fact it adds complexity >> and no additional transparency or ease of programming. Stick to your >> own stupid threads. This one is named "Not about Olcott" in an effort >> to avoid that stupidity. Your lack of knowledge, arrogance, and misuse >> of terminology gives threads the odor of poop. Please return to your >> studies. You have not yet achieved novice status nor are considered an >> earnest performer; just a misguided lost soul. Give it a rest. > > A UTM is the only form of a self-modfying Turing machine that I could > think of. A data driven machine could accomplish the same thing by > modifying its data. I'll see this once again: Your head is fucked. Turing machines do not modify their code; they can modify their tape. How much more basic a fact is there in TM theory????? You really need to accept being an ignorant dumb bunny (or dump shit, take your choice). Since you've been told this several times in messages you've responded to, we cad justify adding stupid to ignorant. -- Jeff Barnett
[toc] | [prev] | [next] | [standalone]
| From | olcott <NoOne@NoWhere.com> |
|---|---|
| Date | 2020-11-24 17:26 -0600 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <ZoCdnW5h7YkpCyDCnZ2dnUU7-dWdnZ2d@giganews.com> |
| In reply to | #25843 |
On 11/24/2020 5:19 PM, Jeff Barnett wrote: > On 11/23/2020 4:34 PM, olcott wrote: >> On 11/23/2020 5:16 PM, Jeff Barnett wrote: >>> On 11/23/2020 2:55 PM, olcott wrote: >>>> On 11/23/2020 3:51 PM, dklei...@gmail.com wrote: >>>>> On Monday, November 23, 2020 at 1:06:29 PM UTC-8, >>>>> malcolm.ar...@gmail.com wrote: >>>>>> On Monday, 23 November 2020 at 19:37:13 UTC, dklei...@gmail.com >>>>>> wrote: >>>>>>> I hope that comp.theory is the best place for the following >>>>>>> question: >>>>>>> >>>>>>> Has it ever been shown that a Turing Machine can do the >>>>>>> kind of neural network calculating done by AI such as Siri? >>>>>>> >>>>>>> This in the context of whether or not such calculating can >>>>>>> legitimately be called algorithmic. It is not algorithmic in >>>>>>> sense Knuth uses the word "algorithm". >>>>>>> >>>>>> "Neural network" was a great marketing term. But all a neural >>>>>> network is is a directed graph, weights, and a sigmoid function to >>>>>> prevent high weights pushing output very high and to make the >>>>>> results continously differentiable to help out the training >>>>>> algorithm. >>>>>> >>>>>> It doesn't emulate a real human brain. >>>>> >>>>> The problem here is that the neural networks continually modify the >>>>> network and a Turing Machine can't be modified on the fly. >>>> >>>> Sure it can. A UTM can simulate its own TDM and modify this TMD at >>>> any point in time. Basically anything that a computer can do some TM >>>> can do. >>>> >>>>> Can we >>>>> use a Turing Machine to simulate another mode of calculating >>>>> (neural nets) and still say that Turing Machine is doing the >>>>> processing. >>>>> That is, assuming a Turing Machine can simulate a neural net. The >>>>> Church-Turing thesis is not a theorem - how sure of it are we? >>> This reply shows how little you know about the subject. Why on earth >>> is a UTM needed for this task? It isn't. In fact it adds complexity >>> and no additional transparency or ease of programming. Stick to your >>> own stupid threads. This one is named "Not about Olcott" in an effort >>> to avoid that stupidity. Your lack of knowledge, arrogance, and >>> misuse of terminology gives threads the odor of poop. Please return >>> to your studies. You have not yet achieved novice status nor are >>> considered an earnest performer; just a misguided lost soul. Give it >>> a rest. >> >> A UTM is the only form of a self-modfying Turing machine that I could >> think of. A data driven machine could accomplish the same thing by >> modifying its data. > > I'll see this once again: Your head is fucked. Turing machines do not > modify their code; A UTM can simulate its own TDM and modify this TMD at any point in time. Basically anything that a computer can do some TM can do. You must be dumber than a box of rocks to not know this. > they can modify their tape. How much more basic a > fact is there in TM theory????? You really need to accept being an > ignorant dumb bunny (or dump shit, take your choice). Since you've been > told this several times in messages you've responded to, we cad justify > adding stupid to ignorant. -- Copyright 2020 Pete Olcott "Great spirits have always encountered violent opposition from mediocre minds." Einstein
[toc] | [prev] | [next] | [standalone]
| From | Jeff Barnett <jbb@notatt.com> |
|---|---|
| Date | 2020-11-24 18:12 -0700 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <rpkb2n$v9q$1@dont-email.me> |
| In reply to | #25847 |
On 11/24/2020 4:26 PM, olcott wrote: > On 11/24/2020 5:19 PM, Jeff Barnett wrote: >> On 11/23/2020 4:34 PM, olcott wrote: >>> On 11/23/2020 5:16 PM, Jeff Barnett wrote: >>>> On 11/23/2020 2:55 PM, olcott wrote: >>>>> On 11/23/2020 3:51 PM, dklei...@gmail.com wrote: >>>>>> On Monday, November 23, 2020 at 1:06:29 PM UTC-8, >>>>>> malcolm.ar...@gmail.com wrote: >>>>>>> On Monday, 23 November 2020 at 19:37:13 UTC, dklei...@gmail.com >>>>>>> wrote: >>>>>>>> I hope that comp.theory is the best place for the following >>>>>>>> question: >>>>>>>> >>>>>>>> Has it ever been shown that a Turing Machine can do the >>>>>>>> kind of neural network calculating done by AI such as Siri? >>>>>>>> >>>>>>>> This in the context of whether or not such calculating can >>>>>>>> legitimately be called algorithmic. It is not algorithmic in >>>>>>>> sense Knuth uses the word "algorithm". >>>>>>>> >>>>>>> "Neural network" was a great marketing term. But all a neural >>>>>>> network is is a directed graph, weights, and a sigmoid function to >>>>>>> prevent high weights pushing output very high and to make the >>>>>>> results continously differentiable to help out the training >>>>>>> algorithm. >>>>>>> >>>>>>> It doesn't emulate a real human brain. >>>>>> >>>>>> The problem here is that the neural networks continually modify the >>>>>> network and a Turing Machine can't be modified on the fly. >>>>> >>>>> Sure it can. A UTM can simulate its own TDM and modify this TMD at >>>>> any point in time. Basically anything that a computer can do some >>>>> TM can do. >>>>> >>>>>> Can we >>>>>> use a Turing Machine to simulate another mode of calculating >>>>>> (neural nets) and still say that Turing Machine is doing the >>>>>> processing. >>>>>> That is, assuming a Turing Machine can simulate a neural net. The >>>>>> Church-Turing thesis is not a theorem - how sure of it are we? >>>> This reply shows how little you know about the subject. Why on earth >>>> is a UTM needed for this task? It isn't. In fact it adds complexity >>>> and no additional transparency or ease of programming. Stick to your >>>> own stupid threads. This one is named "Not about Olcott" in an >>>> effort to avoid that stupidity. Your lack of knowledge, arrogance, >>>> and misuse of terminology gives threads the odor of poop. Please >>>> return to your studies. You have not yet achieved novice status nor >>>> are considered an earnest performer; just a misguided lost soul. >>>> Give it a rest. >>> >>> A UTM is the only form of a self-modfying Turing machine that I could >>> think of. A data driven machine could accomplish the same thing by >>> modifying its data. >> >> I'll see this once again: Your head is fucked. Turing machines do not >> modify their code; > > A UTM can simulate its own TDM and modify this TMD at any point in time. > Basically anything that a computer can do some TM can do. So what????? That's like saying you can modify a digital image of yourself and that has ABSOLUTELY NOTHING to do with saying that you can modify yourself. If you could, we can all suggest several improvements: tone down the arrogance, learn to read, actually learn to learn, as a student keep your mouth shut to you understand the vocabulary, do not visit your sins and lunacy on others, etc. > You must be dumber than a box of rocks to not know this. You must be stupid to think so. You haven't progressed to the point where you are allowed to call people names or evaluate them. Your lack of reading and reasoning abilities have overwhelmed your options in life. >> they can modify their tape. How much more basic a fact is there in TM >> theory????? You really need to accept being an ignorant dumb bunny (or >> dump shit, take your choice). Since you've been told this several >> times in messages you've responded to, we cad justify adding stupid to >> ignorant. You stopped reading in the middle of a sentence, again, and so soiled yourself once more. That's one reason that all of your education has turned to poop for brains. So sad. -- Jeff Barnett
[toc] | [prev] | [next] | [standalone]
| From | Ben Bacarisse <ben.usenet@bsb.me.uk> |
|---|---|
| Date | 2020-11-25 03:33 +0000 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <871rgi8608.fsf@bsb.me.uk> |
| In reply to | #25875 |
Jeff Barnett <jbb@notatt.com> writes: > So what????? That's like saying you can modify a digital image of > yourself and that has ABSOLUTELY NOTHING to do with saying that you > can modify yourself. Snap! I was going to use the same analogy (actually a robot programmed to draw moustaches on photograps), but I decided PO would focus on the analogy and not the technical facts. -- Ben.
[toc] | [prev] | [next] | [standalone]
| From | olcott <NoOne@NoWhere.com> |
|---|---|
| Date | 2020-11-24 21:47 -0600 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <7KKdnT2nCv1VTiDCnZ2dnUU7-d2dnZ2d@giganews.com> |
| In reply to | #25894 |
On 11/24/2020 9:33 PM, Ben Bacarisse wrote: > Jeff Barnett <jbb@notatt.com> writes: > >> So what????? That's like saying you can modify a digital image of >> yourself and that has ABSOLUTELY NOTHING to do with saying that you >> can modify yourself. > > Snap! I was going to use the same analogy (actually a robot programmed > to draw moustaches on photograps), but I decided PO would focus on the > analogy and not the technical facts. > Modifying the master tape location of the currently simulated UTM by this same simulated UTM is self-modification. -- Copyright 2020 Pete Olcott "Great spirits have always encountered violent opposition from mediocre minds." Einstein
[toc] | [prev] | [next] | [standalone]
| From | Ben Bacarisse <ben.usenet@bsb.me.uk> |
|---|---|
| Date | 2020-11-24 23:23 +0000 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <87h7pe9w54.fsf@bsb.me.uk> |
| In reply to | #25757 |
olcott <NoOne@NoWhere.com> writes: > A UTM is the only form of a self-modfying Turing machine that I could > think of. No TM is self-modifying. -- Ben.
[toc] | [prev] | [next] | [standalone]
| From | olcott <NoOne@NoWhere.com> |
|---|---|
| Date | 2020-11-24 17:31 -0600 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <e82dnXWkCo53CiDCnZ2dnUU7-RnNnZ2d@giganews.com> |
| In reply to | #25844 |
On 11/24/2020 5:23 PM, Ben Bacarisse wrote: > olcott <NoOne@NoWhere.com> writes: > >> A UTM is the only form of a self-modfying Turing machine that I could >> think of. > > No TM is self-modifying. > So in other words you are not bright enough to imagine that a UTM could write to its own tape changing the TMD of itself. No wonder you have such a difficult time understanding me. A learned by rote guy rejects anything that they have not already memorized. -- Copyright 2020 Pete Olcott "Great spirits have always encountered violent opposition from mediocre minds." Einstein
[toc] | [prev] | [next] | [standalone]
| From | Jeff Barnett <jbb@notatt.com> |
|---|---|
| Date | 2020-11-24 18:14 -0700 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <rpkb68$v9q$2@dont-email.me> |
| In reply to | #25849 |
On 11/24/2020 4:31 PM, olcott wrote: > On 11/24/2020 5:23 PM, Ben Bacarisse wrote: >> olcott <NoOne@NoWhere.com> writes: >> >>> A UTM is the only form of a self-modfying Turing machine that I could >>> think of. >> >> No TM is self-modifying. >> > > So in other words you are not bright enough to imagine that a UTM could > write to its own tape changing the TMD of itself. No wonder you have > such a difficult time understanding me. A learned by rote guy rejects > anything that they have not already memorized. God! You are grotesquely stupid. You don't get to define what a Turin machine is or does. Ever hear of a guy named Turin .... -- Jeff Barnett
[toc] | [prev] | [next] | [standalone]
| From | olcott <NoOne@NoWhere.com> |
|---|---|
| Date | 2020-11-24 19:37 -0600 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <0YCdnZLP143JKCDCnZ2dnUU7-R2dnZ2d@giganews.com> |
| In reply to | #25876 |
On 11/24/2020 7:14 PM, Jeff Barnett wrote: > On 11/24/2020 4:31 PM, olcott wrote: >> On 11/24/2020 5:23 PM, Ben Bacarisse wrote: >>> olcott <NoOne@NoWhere.com> writes: >>> >>>> A UTM is the only form of a self-modfying Turing machine that I could >>>> think of. >>> >>> No TM is self-modifying. >>> >> >> So in other words you are not bright enough to imagine that a UTM >> could write to its own tape changing the TMD of itself. No wonder you >> have such a difficult time understanding me. A learned by rote guy >> rejects anything that they have not already memorized. > > God! You are grotesquely stupid. You don't get to define what a Turin > machine is or does. Ever hear of a guy named Turin .... Ad hominem the first resort of clueless wonders and/or assholes. -- Copyright 2020 Pete Olcott "Great spirits have always encountered violent opposition from mediocre minds." Einstein
[toc] | [prev] | [next] | [standalone]
| From | Jeff Barnett <jbb@notatt.com> |
|---|---|
| Date | 2020-11-25 11:49 -0700 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <rpm90n$pqc$1@dont-email.me> |
| In reply to | #25881 |
On 11/24/2020 6:37 PM, olcott wrote: > On 11/24/2020 7:14 PM, Jeff Barnett wrote: >> On 11/24/2020 4:31 PM, olcott wrote: >>> On 11/24/2020 5:23 PM, Ben Bacarisse wrote: >>>> olcott <NoOne@NoWhere.com> writes: >>>> >>>>> A UTM is the only form of a self-modfying Turing machine that I could >>>>> think of. >>>> >>>> No TM is self-modifying. >>>> >>> >>> So in other words you are not bright enough to imagine that a UTM >>> could write to its own tape changing the TMD of itself. No wonder you >>> have such a difficult time understanding me. A learned by rote guy >>> rejects anything that they have not already memorized. >> >> God! You are grotesquely stupid. You don't get to define what a Turin >> machine is or does. Ever hear of a guy named Turin .... > > Ad hominem the first resort of clueless wonders and/or assholes. Not ad hominem. Since you make the same mistakes over and over again, one may draw the conclusion that you are grotesquely stupid. It's logic, not a personal attack. You can't seem to tell the difference. -- Jeff Barnett
[toc] | [prev] | [next] | [standalone]
| From | Ben Bacarisse <ben.usenet@bsb.me.uk> |
|---|---|
| Date | 2020-11-25 21:30 +0000 |
| Subject | Re: Church-Turing thesis |
| Message-ID | <87blfl6s69.fsf@bsb.me.uk> |
| In reply to | #25849 |
olcott <NoOne@NoWhere.com> writes: > On 11/24/2020 5:23 PM, Ben Bacarisse wrote: >> olcott <NoOne@NoWhere.com> writes: >> >>> A UTM is the only form of a self-modfying Turing machine that I could >>> think of. >> >> No TM is self-modifying. > > So in other words you are not bright enough to imagine that a UTM > could write to its own tape changing the TMD of itself. No wonder you > have such a difficult time understanding me. A learned by rote guy > rejects anything that they have not already memorized. That is a stupid remark. You would have to start be reading a book about this topic for there to be any reasonable chance of explaining why you are writing nonsense. For everyone else: all TMs (except for trivial do-nothing TMs) modify their tape. That is not self-modifying. Even if a TM is passed its own description to run, it can't self-modify. That is true regardless of whether the TM is a UTM or not. A UTM, passed its own encoding, can change that data but not itself (and it is very unlikely to be a UTM in that case). No matter how many levels of UTMs simulating UTMs one imagines, with all of them scribbling all over the tape (and the simulated tape), there is only one Turing machine, and it remain unaltered throughout. -- Ben.
[toc] | [prev] | [next] | [standalone]
| From | Richard Damon <Richard@Damon-Family.org> |
|---|---|
| Date | 2020-11-23 17:02 -0500 |
| Message-ID | <vjWuH.24544$093.16008@fx05.iad> |
| In reply to | #25740 |
On 11/23/20 4:51 PM, dklei...@gmail.com wrote: > On Monday, November 23, 2020 at 1:06:29 PM UTC-8, malcolm.ar...@gmail.com wrote: >> On Monday, 23 November 2020 at 19:37:13 UTC, dklei...@gmail.com wrote: >>> I hope that comp.theory is the best place for the following >>> question: >>> >>> Has it ever been shown that a Turing Machine can do the >>> kind of neural network calculating done by AI such as Siri? >>> >>> This in the context of whether or not such calculating can >>> legitimately be called algorithmic. It is not algorithmic in >>> sense Knuth uses the word "algorithm". >>> >> "Neural network" was a great marketing term. But all a neural >> network is is a directed graph, weights, and a sigmoid function to >> prevent high weights pushing output very high and to make the >> results continously differentiable to help out the training algorithm. >> >> It doesn't emulate a real human brain. > > The problem here is that the neural networks continually modify the > network and a Turing Machine can't be modified on the fly. Can we > use a Turing Machine to simulate another mode of calculating > (neural nets) and still say that Turing Machine is doing the processing. > That is, assuming a Turing Machine can simulate a neural net. The > Church-Turing thesis is not a theorem - how sure of it are we? > For a Turing Machine, all the neural stuff would be on the tape, not in the fixed state machine. The fixed state machine would be the core code for the rules of how neurons interract. The actual neural network with weights and all that would be on the tape.
[toc] | [prev] | [next] | [standalone]
| From | Jeff Barnett <jbb@notatt.com> |
|---|---|
| Date | 2020-11-23 15:56 -0700 |
| Message-ID | <rphen5$ojf$3@dont-email.me> |
| In reply to | #25740 |
On 11/23/2020 2:51 PM, dklei...@gmail.com wrote: > On Monday, November 23, 2020 at 1:06:29 PM UTC-8, malcolm.ar...@gmail.com wrote: >> On Monday, 23 November 2020 at 19:37:13 UTC, dklei...@gmail.com wrote: >>> I hope that comp.theory is the best place for the following >>> question: >>> >>> Has it ever been shown that a Turing Machine can do the >>> kind of neural network calculating done by AI such as Siri? >>> >>> This in the context of whether or not such calculating can >>> legitimately be called algorithmic. It is not algorithmic in >>> sense Knuth uses the word "algorithm". >>> >> "Neural network" was a great marketing term. But all a neural >> network is is a directed graph, weights, and a sigmoid function to >> prevent high weights pushing output very high and to make the >> results continously differentiable to help out the training algorithm. >> >> It doesn't emulate a real human brain. > > The problem here is that the neural networks continually modify the > network and a Turing Machine can't be modified on the fly. Can we > use a Turing Machine to simulate another mode of calculating > (neural nets) and still say that Turing Machine is doing the processing. > That is, assuming a Turing Machine can simulate a neural net. The > Church-Turing thesis is not a theorem - how sure of it are we? A C neural net program keeps its net in storage; a TM neural net keeps its net on its tape. So what's the problem with modifying the tape? None! That's mostly what TMs do. -- Jeff Barnett
[toc] | [prev] | [next] | [standalone]
Page 2 of 3 — ← Prev page 1 [2] 3 Next page →
Back to top | Article view | comp.theory
csiph-web