Discussion of article "Population optimization algorithms: Saplings Sowing and Growing up (SSG)" - page 9

New comment
 
mytarmailS #:
The fitness function is a subspecies of the objective function, aka the fitness function, the fitness is the error.

no.

please do not litter the article thread with heresy.

 

There's just a terminological confusion.


Using the example of an Expert Advisor.

  • Theoptimisation criterion is OnTester. It may not change in different Expert Advisors. I.e. the OnTester source is the same.
  • FF - Expert Advisor+Price History+OnTester. If you change the optimisation interval, the FF changes, if you change the Expert Advisor, the FF changes.
 
Andrey Dik #:

no.

please don't litter the article thread with heresy.

At least read Wikipedia and don't talk heresy and disgrace yourself
 

FF - literally means "fitness function". FF is the same as "evaluation criteria".

The formalisation of FF is OnTester (), i.e. FF formula.

When they say"FF value ", they mean the result of evaluating an EA with certain parameters.

When they say"FF surface ", they mean the results of evaluating multiple sets of EA parameters on a certain segment of history.

If we change the segment or the length of history, the FF value (the FF itself has not changed) of the Expert Advisor with certain parameters separately will change, and accordingly the FF surface as the results of multiple sets of parameters of the Expert Advisor will change.

We see that the FF does not change and its formalisation - OnTester () - does not change, but the FFvalues change.

FFvalue is the estimation of one set of parameters.

FFsurface - estimates of multiple sets of parameters.

Thus, the value of a single run and the surface of a set of runs change, while the FF remains unchanged.

 
mytarmailS #:
At least read Wikipedia and don't talk heresy and disgrace yourself.

"Don't teach your father and basta".

I suppose you have a lot of publications on the subject, which can be read and there are works, the results of which are used all over the world?

wikipedia is not an authority for me, everyone writes there, including outright rubbish.

Any specific suggestions on how to improve my publicly published algorithms? - welcome, correct and publish them, but if not, please pass by.

 
Andrey Dik #:
it makes no difference if the FF is static or dynamically changing! the point is how fast the AO is .....


Andrey Dik #:

so, the value of a single run and the surface of many runs change, the FF is unchanged.

It's called contradicting yourself...

that's what I was pointing out.

 
Andrey Dik #:

"don't teach your father and basta."

I suppose you have a lot of publications on the subject, which can be read, and there are works, the results of which are used all over the world?

wikipedia is not an authority for me, everyone writes there, including outright rubbish.

Any specific suggestions on how to improve my publicly published algorithms? - welcome, correct and publish them, but if not, please pass by.

"Don't learn from your great-grandfather, dandy."

wikipedia is not an authority, but the free fantasies of incompetent passersby who for some reason called articles, it is an authority????. .... powerful... You can see a thinking man.


So all the TS and ideas described in MQL "articles" work? Oh none of them work, how can it be so? This is the article ))))

 
mytarmailS #:


it's called talking against yourself.

that's what I was pointing out.


So even a hedgehog can see that it's about meaning and surface, I've chewed it all up above.
 
mytarmailS #:

"don't teach your great-grandfather, dandy."

wikipedia is not an authority, but the free fantasies of incompetent scoundrels, which for some reason called articles, it is an authority???? .... powerful... You can see that you're a thinking person.


So all the TS and ideas described in MQL "articles" work? Oh none of them work, how can it be so? This is the article )))).


I can't be responsible for other MQL articles, but there people have done something and shared it, unlike you.
In wikipedia, it's just a simple writing of people who are not responsible, moreover, politicised writing.
as for my articles - what exactly doesn't work? stop talking and do something.
 
mytarmailS #:
What did I write? Don't you read?

Taken out of context. Read on.
I was saying that the correctness of choosing a point on the OP does not depend on a hill or a depression and not even on the velocity of the local motion vector in time, but only on the sign of the acceleration vector (derivative of velocity), one part of which is in the future, which is not known.
12345678910111213
New comment