[Turkmath:6074] Re: 2000 den beri 'Alien Calculus' diye bir konu varmış da benim şimdi haberim olmuş...!

H. Turgay Kaptanoglu kaptan at fen.bilkent.edu.tr
Mon Apr 17 12:28:49 UTC 2023


Merhabalar,

Su asagidaki yazida birkac matematiksel yanlis var.

1.
> absolutely convergent ama kendisi divergent serilerde, (conditionally
> convergent)

"Kendisi yakinsak, ama mutlak yakinsak olmayan" olmali.

2.
> **Now, let's rearrange the terms of this series by grouping the 
> positive
> and negative terms separately:*
> 
> *1 + 1/3 + 1/5 + 1/7 + ... - 1/2 - 1/4 - 1/6 - 1/8 - ...*
> 
> *This rearrangement still converges to the same value as the original
> series, which is ln(2), ...

Bu yeniden duzenleme sonsuz eksi sonsuz verdigi icin bu toplam tanimsiz,
dolayisiyla ln(2)'ye esit olamaz.

3.
> *For instance, to get the value of Pi, we can rearrange the terms as
> follows:*
> 
> *1 - 1/3 + 1/5 - 1/7 + 1/9 - 1/11 + ...*
> 
> *This rearranged series converges to Pi/4, ...

Bu seri o noktaya kadar sozu edilen almasik harmonik serinin bir yeniden
duzenlemesi degil, baska bir seri.

=====
H. Turgay Kaptanoğlu
www.fen.bilkent.edu.tr/~kaptan/


On 14.04.2023 12:58, yilmaz akyildiz wrote:
> Dahası, '*Alien Calculus*' parçacık fiziğini  sonsuzluklardan
> kurtarabilecekmiş... !
> Daha dahası, boynuz kulağı geçmiş ve bu konunun üstatları arasında genç
> türk fizikçilerimiz de yerlerini almıııış...
> 
> Öğrencilerimizde Fizikteki sonsuzların *Feynman* gibi "sihirbazlarca"
> ad-hoc  yani  hokus-pokus metotlarla la bertaraf edilip deneylerle 
> 10^(-12)
> mertebelerinde uyuşan rakamlar bulduklarını ve Nobel Ödülleri 
> aldıklarını
> duymuştuk. Bendeniz işin sırrını öğrenmeden fiziği bırakıp biraz 
> matematik
> öğreneyim istemiştim. Yine de Fizikten uzak durmamış örneğin (70 lerin
> tabiki Dunford - Schwartz ın Jack Schwartz un dan sonra, en meşhur
> fonksiyonel analizcilerinden, ...)  arthur Jaffe  ve james Glimm' in 2
> boyutta rigorous  (kesin) Constructive Quantum Field Theory ekolünü bir
> süre takip etmiş ve hatta acaba bu konuda mı tez yazsam demiştim, 
> (Tengri
> beni esirgemiş...).
> Bu teori 4 boyuta çıkartılamadı ve geriye birkaç makale  bırakarak
> ortalıktan kaybolup gitti..[image: WhatsApp Image 2023-04-13 at
> 14.56.23.jpeg]
> Ardından duyduk ki bazi meşhur başka Fonksiyonel Analizciler (such as 
> Barry
> Simon of Caltech) Feynman Path İntegralini regirous temellere oturtmaya
> çalışıyorlar. Kolay mı sanıyorsunuz? Netekim o da başarılı olmadı.  
> Benim
> bunlardan aldığım ders:
> *Fizikte ki matematiğin regirous olmasını beklerseniz *
> *bir süre sonra tıkanır kalır, fizik de yapamazsınız..!*
> Az gittim uz gittim her ne kadar dere tepe düz gittim se de
> sonunda döndüm dolaştım dün yine fizikteki bu sonsuzluklarla 
> karşılaştım:
> https://www.quantamagazine.org/alien-calculus-could-save-particle-physics-from-infinities-20230406/?fbclid=IwAR1qsG3rffzDZ14nTBxAr6eG5uGLRuyPoV6K58aP9Gz9mG72kVEbVnSKNAc
> 
> Fırından yeni çıkmış yukarıdakki linkteki  yarı-bilimsel aydınlatıcı
> makaleyi sizlerle paylaşmadan edemezdim... İki nedenden:
> *1. *yeni bir calculus den bahsediliyor: *Alien Calculus,*
> parçacık fiziğini  sonsuzluklardan kurtarabilecekmiş... !  Bana biraz
> fransız geldi, zaten de bulucusu da bir Fransız: *Jean Écalle  *
> *2. *boynuz kulağı geçmiş ve bu konunun üstatları arasında genç türk
> fizikçilerimiz de yerlerini almış:
>                                               
> https://youtu.be/Sq_tfbgHQlU
> 
> linkteki yazıdan bir kaç not:
> *Divergent series are the invention of the devil, *
> *and it is a shame to base on them any demonstration whatsoever.. *
> *Niels Henrik Abel (1828)*
> Bu satırları okuyunca *ali ülger geldi aklıma. *bu konuda
> yani divergent seriler konusunda epey bilgilidir kendisi,
> o da susuverdi son zamanlarda,
> susan bir kişi daha var aşağıda ona da geleceğim.
> 
> Şu gerçek beni delirtmişti ilk farkına vardığımda:
> absolutely convergent ama kendisi divergent serilerde, (conditionally
> convergent)
> örneğin alternating harmonic seri: 1-1/2+1/3-1/4... = Ln(2),
> bu serilerde terimlerin yerleri değiştirilerek  "*herhangi bir sayı*" 
> elde
> edilebilir...
> Ali Ülger e bir soru: "*herhangi bir sayı*"  demek doğru mu?
> bütün reel sayılar mı yoksa Ln(2 ) gibi onlarda mı transendental?.
> Durun bu soruyu Ali den önce chatGPT ye soralım:
> *heyyy chatGPT, here is a question for you: *
> *consider an absolutely divergent , but conditionally convergent 
> series.
> e.g. alternating harmonic series. by rearranging its terms, what type 
> of
> numbers can you get?*
> ChatGPT:
> 
> *When we rearrange the terms of a conditionally convergent series, we 
> can
> get any real number, including irrational numbers and even infinity. 
> **One
> way to see this is to consider the Riemann rearrangement theorem, which
> states that given any conditionally convergent series, we can rearrange 
> its
> terms to converge to any desired real number, or to diverge to positive 
> or
> negative infinity. **For example, let's consider the alternating 
> harmonic
> series: **1 - 1/2 + 1/3 - 1/4 + 1/5 - 1/6 + ...**This series is
> conditionally convergent, which means that the series converges, but 
> not
> absolutely (i.e., the series of the absolute values of its terms 
> diverges).
> **Now, let's rearrange the terms of this series by grouping the 
> positive
> and negative terms separately:*
> 
> *1 + 1/3 + 1/5 + 1/7 + ... - 1/2 - 1/4 - 1/6 - 1/8 - ...*
> 
> *This rearrangement still converges to the same value as the original
> series, which is ln(2), but the rearrangement can now be used to obtain 
> any
> real number.*
> 
> *For instance, to get the value of Pi, we can rearrange the terms as
> follows:*
> 
> *1 - 1/3 + 1/5 - 1/7 + 1/9 - 1/11 + ...*
> 
> *This rearranged series converges to Pi/4, so by multiplying it by 4, 
> we
> obtain Pi.*
> 
> *Therefore, by rearranging the terms of a conditionally convergent 
> series, **we
> can get any real number, including irrational numbers and even 
> infinity.*
> 
> Geri Abel' e gidelim tekrar, ne anladım şimdi ben şunlardan:
> 
> *Ramanujan Toplamı: 1+2+3+4+5+6+…= -1/12*
> *To most physicists, the inevitable divergence of even the simplest 
> quantum
> field theory remains an abstract problem, like the death of our sun in 
> a
> billion or so years. At a time when calculating — much less testing — 
> even
> the 10th term of the series seems like science fiction, why fret about
> dangers lurking far beyond the 100th? But to a select few, the fact 
> that
> the best-understood theory in modern physics technically yields 
> infinite
> answers to any question you might care to ask remains deeply 
> disturbing.
> “We do not know how to simulate the world, even in principle, even with
> unlimited computational resources,” said Emanuel Katz
> <https://www.bu.edu/physics/profile/emanuel-katz/>, a physicist at 
> Boston
> University who studies new methods for going beyond Feynman diagrams.*
> 
> Ali Ülger yanında sesi artık çıkmayan 2. kişiden bahsedecektim:
> *Nihat Berker*
> son günlerde okuduğum feynman graphs, infinite series, perturbation vbg
> konularına yakın veya belkide aynısı değil mi Berker in 
> "*renormalization*"
> konusu?
> Bu soruyu da Cihan a sormuş olayım!
> kalın sağlıcakla,
> y.a.
> 
> _______________________________________________
> Turkmath mailing list
> Turkmath at listweb.bilkent.edu.tr
> http://yunus.listweb.bilkent.edu.tr/cgi-bin/mailman/listinfo/turkmath


More information about the Turkmath mailing list