Practical advice, please. - page 3
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Select the first line.
The minimum maximum in the first stack, but the average error of the first row is the largest... )))
I'll add...
Find the maximum, calculate the average and, depending on the average, adjust the maximum. And then choose by the minimum maximum. You have to come up with a formula for correcting the maximum, and there should be a coefficient. And the value of the coefficient should be picked up mentally.
Purely and simply, multiply the maximum by the average and multiply by the coefficient. Changing the coefficient, see what variant becomes the best - this is how to pick up the coefficient.
"Purely stupid" ))) Took the coefficient (and why not) Min.ValuesTable/Max.ValuesTable. Only which variant is better - that's what we need to find out, not pick the best coefficient to the unknown ))
P.S. The second line got the lowest value...Another option. Off-topic, but also a way. Don't look at percentages, but like a rating. Each column is a whole number from 1 to 3 (or 1, 1, 2, etc.). Then calculate the average rating.
Another option. Do a two-step selection. Choose several ones with the best mean, and from them choose the one with the best maximum. Or vice versa, select a few best maxima, and choose the one with the best average.
You mean not by modules, but by layers?
Change the form of matrix ModN[3][15]
;))
Thanks, Roman, I'll give it a try. Question, what is the best value?
.............
It's not about errorfree.
For example we have two error responses of 0.2 and 0.0000001. 0.00000002 (especially problems will occur if one of the estimates is just 0) - which is quite inconvenient to visually estimate the number of these zeros. So it's easier to reflect by making the best score 1.... we just get 1-0.2 + 1 -0.00000001 . 0.8 and 0.99999999 ... it is clear that by multiplying these values we end up with 0.8 total quality...... if both scores were 0.8 then the answer would be 0.64.... This option is the simplest.
It's easier to do and see the total
I think I got it. I'll give it a try. But to be honest, I do not quite understand why this is so ... )))
I've been watching you for a long time. Interesting personality. Respect.
In any context, historical data can only be used in conjunction with the current environment. This is important. Historical data, no matter how good it is, is negative. What is my point? Market prices are not a projectile following a certain trajectory.
Thank you ))))
It's not a question of usage. It's a question of learning. How do you teach without history? Or how do you bolt "now" to "already been"?
I understand that every module is trained on data, which, in principle, may never be repeated. But the training data isn't made by copy, is it? )) And we check it on the data known to me but not to the modules. Besides, the main module is learning from completely unknown data...
By the way, the network's final response, with any parameters, produces 0.00% of errors. But I understand that this is just a training session. In reality everything will not be so beautiful. That is why I want to understand which set of errors modules is more .... "promising" or something, more .... "stable"....
"Purely stupid" )))) Took the coefficient (and why not) Min.ValuesTable/Max.ValuesTable. Only which variant is better - that's what we need to find out, not pick the best coefficient for the unknown ))
P.S. The second line has the lowest value...The point is that this problem cannot be solved unambiguously or by any mathematical rule. It's a fuzzy logic problem. Exactly how you calculate which of the strings is more appropriate is the coefficient to use.
It's the percentage of something that counts, and the rating itself counts.
That's the thing, this problem is not solved unambiguously or by any mathematical rule. It is a fuzzy logic problem. Exactly how you calculate which of the rows is more appropriate is the coefficient to use.
Dimitri, the table is planned to have at least 10 rows. How do I choose the most suitable one? Suppose I chose. In that case, I don't need any coefficients at all ))) Isn't it so?
Dimitri, the table is planned to have at least 10 rows. How do I choose the most appropriate one? Suppose I've chosen. Then I don't need any coefficients at all ))) Isn't it so?
Once you've selected the coefficient on the basis of empirical data so that it meets your needs, and then you automate the selection for other data.
If there won't be any other data in the future and you only need to make a right choice once, you must use additional criteria or use "personal taste".
There is no such theorem or formula in mathematics.