pharo-users@lists.pharo.org

Any question about pharo is welcome

View all threads

Agile Artificial Intelligence

SD
Stéphane Ducasse
Wed, Jul 1, 2020 7:02 PM

We are happy to announce that the book of A. Bergel is out

https://www.apress.com/gp/book/9781484253830

Agile Artificial Intelligence in Pharo

Implementing Neural Networks, Genetic Algorithms, and Neuroevolution

Cover classical algorithms commonly used as artificial intelligence techniques and program agile artificial intelligence applications using Pharo in this book. It takes a practical approach by presenting the implementation details to illustrate the numerous concepts it explain…

https://www.amazon.com/Agile-Artificial-Intelligence-Pharo-Neuroevolution/dp/1484253833/ref=tmm_pap_swatch_0?_encoding=UTF8&qid=1593398066&sr=8-1

As a book author I want to congratulate alex for this effort.

S.


Stéphane Ducasse http://stephane.ducasse.free.fr / http://www.pharo.org 03 59 35 87 52 Assistant: Aurore Dalle FAX 03 59 57 78 50 TEL 03 59 35 86 16 S. Ducasse - Inria 40, avenue Halley, Parc Scientifique de la Haute Borne, Bât.A, Park Plaza Villeneuve d'Ascq 59650 France

We are happy to announce that the book of A. Bergel is out https://www.apress.com/gp/book/9781484253830 Agile Artificial Intelligence in Pharo Implementing Neural Networks, Genetic Algorithms, and Neuroevolution Cover classical algorithms commonly used as artificial intelligence techniques and program agile artificial intelligence applications using Pharo in this book. It takes a practical approach by presenting the implementation details to illustrate the numerous concepts it explain… https://www.amazon.com/Agile-Artificial-Intelligence-Pharo-Neuroevolution/dp/1484253833/ref=tmm_pap_swatch_0?_encoding=UTF8&qid=1593398066&sr=8-1 As a book author I want to congratulate alex for this effort. S. -------------------------------------------- Stéphane Ducasse http://stephane.ducasse.free.fr / http://www.pharo.org 03 59 35 87 52 Assistant: Aurore Dalle FAX 03 59 57 78 50 TEL 03 59 35 86 16 S. Ducasse - Inria 40, avenue Halley, Parc Scientifique de la Haute Borne, Bât.A, Park Plaza Villeneuve d'Ascq 59650 France
TT
Tomaž Turk
Thu, Jul 2, 2020 7:56 AM

Thanks, Stef, the book is excellent!

Best wishes, Tomaz

Thanks, Stef, the book is excellent! Best wishes, Tomaz
SD
Stéphane Ducasse
Thu, Jul 2, 2020 8:35 AM

write it on amazon :)

On 2 Jul 2020, at 09:56, Tomaž Turk tomaz.turk@ef.uni-lj.si wrote:

Thanks, Stef, the book is excellent!

Best wishes, Tomaz


Stéphane Ducasse http://stephane.ducasse.free.fr / http://www.pharo.org 03 59 35 87 52 Assistant: Aurore Dalle FAX 03 59 57 78 50 TEL 03 59 35 86 16 S. Ducasse - Inria 40, avenue Halley, Parc Scientifique de la Haute Borne, Bât.A, Park Plaza Villeneuve d'Ascq 59650 France

write it on amazon :) > On 2 Jul 2020, at 09:56, Tomaž Turk <tomaz.turk@ef.uni-lj.si> wrote: > > Thanks, Stef, the book is excellent! > > Best wishes, > Tomaz -------------------------------------------- Stéphane Ducasse http://stephane.ducasse.free.fr / http://www.pharo.org 03 59 35 87 52 Assistant: Aurore Dalle FAX 03 59 57 78 50 TEL 03 59 35 86 16 S. Ducasse - Inria 40, avenue Halley, Parc Scientifique de la Haute Borne, Bât.A, Park Plaza Villeneuve d'Ascq 59650 France
TT
Tomaž Turk
Fri, Jul 3, 2020 8:11 PM
https://www.amazon.de/Agile-Artificial-Intelligence-Pharo-Neuroevolution/dp/1484253833/ref=sr_1_2?dchild=1&keywords=artificial+intelligence+pharo&qid=1593807040&sr=8-2 Best wishes Tomaz
AB
Alexandre Bergel
Sat, Jul 4, 2020 1:27 AM

Thanks Tomaž for your nice words. Comments on amazon are really important.

Cheers, Alexandre

,.;:~^~:;.,.;:~^~:;.,.;:~^~:;.,.;:~^~:;.,.;: Alexandre Bergel  http://www.bergel.eu ^~:;.,.;:~^~:;.,.;:~^~:;.,.;:~^~:;._,.;:~^~:;.

Thanks Tomaž for your nice words. Comments on amazon are really important. Cheers, Alexandre -- _,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;: Alexandre Bergel http://www.bergel.eu ^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;. > On 03-07-2020, at 16:11, Tomaž Turk <tomaz.turk@ef.uni-lj.si> wrote: > > https://www.amazon.de/Agile-Artificial-Intelligence-Pharo-Neuroevolution/dp/1484253833/ref=sr_1_2?dchild=1&keywords=artificial+intelligence+pharo&qid=1593807040&sr=8-2 <https://www.amazon.de/Agile-Artificial-Intelligence-Pharo-Neuroevolution/dp/1484253833/ref=sr_1_2?dchild=1&keywords=artificial+intelligence+pharo&qid=1593807040&sr=8-2> > > Best wishes > Tomaz
B
bentai
Fri, Aug 21, 2020 5:31 AM

I noticed that if I trained the OR gate with 31 iterations, the first test would fail.

If I train with 32 iterations, then the test for #(0 0) would pass.

What is the explanation for this "tipping point"?

The other tests pass, even if timeRepeat := 1.

I just decided to experiment a bit.

-- Sent from: http://forum.world.st/Pharo-Smalltalk-Users-f1310670.html

I noticed that if I trained the OR gate with 31 iterations, the first test would fail. If I train with 32 iterations, then the test for #(0 0) would pass. What is the explanation for this "tipping point"? The other tests pass, even if timeRepeat := 1. I just decided to experiment a bit. -- Sent from: http://forum.world.st/Pharo-Smalltalk-Users-f1310670.html
AB
Alexandre Bergel
Mon, Oct 5, 2020 1:29 AM

Hello,

Sorry to reply late. I just saw this email.

Each training modify the weights and bias of the perceptron by a small quantity. It is just that, in this very particular case, from 31 or 32 is the drop that makes all things change...

Cheers, Alexandre

,.;:~^~:;.,.;:~^~:;.,.;:~^~:;.,.;:~^~:;.,.;: Alexandre Bergel  http://www.bergel.eu ^~:;.,.;:~^~:;.,.;:~^~:;.,.;:~^~:;._,.;:~^~:;.

On 21-08-2020, at 01:31, bentai bentaisan@gmail.com wrote:

I noticed that if I trained the OR gate with 31 iterations, the first test would fail.

If I train with 32 iterations, then the test for #(0 0) would pass.

What is the explanation for this "tipping point"?

The other tests pass, even if timeRepeat := 1.

I just decided to experiment a bit.

-- Sent from: http://forum.world.st/Pharo-Smalltalk-Users-f1310670.html

Hello, Sorry to reply late. I just saw this email. Each training modify the weights and bias of the perceptron by a small quantity. It is just that, in this very particular case, from 31 or 32 is the drop that makes all things change... Cheers, Alexandre -- _,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;: Alexandre Bergel http://www.bergel.eu ^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;. > On 21-08-2020, at 01:31, bentai <bentaisan@gmail.com> wrote: > > I noticed that if I trained the OR gate with 31 iterations, the first test > would fail. > > If I train with 32 iterations, then the test for #(0 0) would pass. > > What is the explanation for this "tipping point"? > > The other tests pass, even if timeRepeat := 1. > > I just decided to experiment a bit. > > > > -- > Sent from: http://forum.world.st/Pharo-Smalltalk-Users-f1310670.html >