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

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/... <https://www.amazon.de/Agile-Artificial-Intelligence-Pharo-Neuroevolution/dp/...>

Best wishes Tomaz

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