Interpolation, approximation and the like (alglib package) - page 5
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
Okay. So what's the right way to say "analytically defined"? Or should I say "given by analytical expression." Right?
I'm not familiar with the terminology. The same module is a piecewise defined function. Whether to consider it analytical or not - I do not remember.
we dont care about indicators or anything else at this moment, end can use freamwork for any strategy and get the best result that can't be calculated analytically.
Great!!!
You mean from raw price data the neural network itself will develop it's own algorithm and function selection for a specific price segment using reinforcement learning and converge itself over time by continuously learning and minimising the error and storing the values in a text file for future use.
Also, if I am not wrong, in this case we don't need any separate MT5 optimisation for this system since it is continuously learning and saving the data to text files. Am I correct?
Great!!!
You mean from raw price data the neural network itself will develop it's own algorithm and function selection for a specific price segment using reinforcement learning and converge itself over time by continuously learning and minimising the error and storing the values in a text file for future use.
Also, if I am not wrong, in this case we don't need any separate MT5 optimisation for this system since it is continuously learning and saving the data to text files. Am I correct?
1. yes
2. its next and easy step... if 1-st step will work good :)
1. yes
2. its next and easy step... if 1-st step will work good :)
Amazing!!!
By the way, I don't know how much time you will take to implement it practically and make it workable in MT5. But once it is done and done correctly, then probably it will take a couple of months of trials and errors to achieve excellence to beat the forex market and forex market will no longer be a challenge anymore :))
Your system will be the forex equivalent of "ALPHA GO ZERO" for a game like "GO"...GOOD LUCK:)))
I will be waiting for your next article of machine learning with this implementation.
Amazing!!!
By the way, I don't know how much time you will take to implement it practically and make it workable in MT5. But once it is done and done correctly, then probably it will take a couple of months of trials and errors to achieve excellence to beat the forex market and forex market will no longer be a challenge anymore :))
Your system will be the forex equivalent of "ALPHA GO ZERO" for a game like "GO"...GOOD LUCK:)))
I will be waiting for your next article of machine learning with this implementation.
When I find a good features transformer the article will be done, and then you can test it for different strategies
In the quote above, one word is highlighted in red. This is the function that is interpolated, but it is an interpolated function that is defined tabularly (i.e. data series). Which function is more appropriate to call, a tabular (data series) function, or a mathematical formula like y=k*x, y=x^2? I think the latter is the mathematical one. So an expression like "interpolation of a function" looks wild.
And here's the reason, I guess - the title in a reputable book: "Interpolation and Approximation of Functions". Here the word "functions" refers to "approximation" and the word "interpolation" itself. Someone split the title and got two titles "interpolation of functions" and "approximation of functions".
Approximation of functions, i.e. approximation of functions, is OK. One takes a mathematical function, selects its coefficients and thus approximates to data given tabularly.
Interesting reasoning.
Indeed, the task "interpolate function y=x^2" looks meaningless. There is 1) no need to simplify it and, most importantly, 2) the interpolation problem is underdetermined - its domain is not defined, i.e. the set of pairs (x, y) - known points through which it passes.
Intuitively, without specifying the area of definition, having the notation y=x^2, we think that it is valid on the whole numerical axis x. And we don't need to look for the value between the known nodes, it is already known and instantly calculated using the formula. The problem of iterpolation does not exist.
If on x-axis there is a countable set of points I where y-values are known, then you can find intervals between them and on the set J you can set the problem of searching for y-values for intermediate values of x. That is, outside the definition area of a given function I - where it is undefined, on J. As, in fact, you have written yourself. If the bounds of J on the x-axis are outside the bounds of I, this would be an interpolation problem; if the bounds of J on the x-axis are outside the bounds of I, this would be an extrapolation problem.
What to call a function. Of course, there are many meanings of this word in Russian, from kidney dysfunction to distribution of work in a team. We are interested in the approach developed in mathematics. At the engineering level, these things are not paid attention to, but mathematicians are now so https://neerc.ifmo.ru/wiki/index.php?title=%D0%9E%D1%82%D0%BE%D0%B1%D1%80%D0%B0%D0%B6%D0%B5%D0%BD%D0%B8%D1%8F:
A mapping consists of three objects: set A(from), set B(where) and rule f(how).
Then, from post 1:
With Y it is clear, but in what form should X be given? There is, as usual, no reference information in the alglib.
Then, from post 1:
Y is clear, but in what form should X be set? There is, as usual, no reference information in the alglib.
You're good with English, so set it the way it's written: spline nodes (points of x where function is given) and function values at those nodes. Is anything wrong?
Interesting reasoning.
Indeed, the problem "interpolate function y=x^2" looks meaningless. It 1) and there is no need to simplify it, and, most importantly, 2) the interpolation problem is underdetermined - the definition area is not given, that is, the set of pairs (x, y) - known points through which it passes.
Intuitively, without specifying the area of definition, having the notation y=x^2, we think that it is valid on the whole numerical axis x. And we don't need to look for the value between the known nodes, it is already known and instantly calculated using the formula. The problem of iterpolation does not exist.
If on x-axis there is a countable set of points I where y-values are known, then you can find intervals between them and on the set J you can set the problem of searching for y-values for intermediate values of x. That is, outside the definition area of a given function I - where it is undefined, on J. As, in fact, you have written yourself. If the bounds of J on the x-axis are outside the bounds of I, this would be an interpolation problem; if the bounds of J on the x-axis are outside the bounds of I, this would be an extrapolation problem.
What to call a function. Of course, there are many meanings of this word in Russian, from kidney dysfunction to distribution of work in a team. We are interested in the approach developed in mathematics. At the engineering level, these things are not paid attention to, but with mathematicians it is so now https://neerc.ifmo.ru/wiki/index.php?title=%D0%9E%D1%82%D0%BE%D0%B1%D1%80%D0%B0%D0%B6%D0%B5%D0%BD%D0%B8%D1%8F:
You don't seem to have practically solved the problem of interpolation, do you? Yes? In interpolation, you don't talk about simplifying a function. The point of interpolation is not to simplify. Someone lumped interpolation and approximation under one heading in a textbook and there you go...
Why specify the domain of a function that is already defined from minus infinity to plus infinity?
As mathematical gurus write textbooks - a dump of all in one chapter, so on these textbooks senior lecturers give lectures and the same dump goes to the heads of students, some of which later become teachers and the cycle closes. Then some of them, instead of explaining the meaning of established definitions, introduce new ones... instead of a function, it's a mapping and it's a dead end. Some are loaded with all this terminology and think that they have become mathematicians... some kind of disease of leftism in communism.
The terminology is not well versed. The same module is a piecewise defined function. Whether to consider it analytical or not - I don't remember.
Perhaps the most appropriate word would be "formula". On the one hand a function defined by a table with data, and on the other hand a function defined by a formula.