Machine learning in trading: theory, models, practice and algo-trading - page 3391
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
An epiphany is something that doesn't just pop into your head.
you either find a pattern in the order of the pixels, if there is one, or you don't.You won't find a pattern because you have to look at the picture as a matrix, through the convolution window, that is at once by columns and by terms and with size invariant, rotation. Vector representation won't give anything useful there.
and what to do
and what to do
Interesting guy with interesting thoughts, confused traders will be interested :) Because trading and MO are like insanity in themselves.
Looking wider
Sequence and time series are two different concepts, although they have much in common.
A sequence is an ordered set of elements that can be represented as a list or a sequence of numbers, objects, or events. A sequence does not necessarily have a temporal relationship between elements, it is simply an ordered set.
A time series is a special kind of sequence where each element represents the value of a variable measured at different points in time. Thus, a time series is a sequence of data measured at consecutive points in time and is commonly used to analyse the change in a variable over time.
Thus, the main difference between a sequence and a time series is that a time series is a sequence of data measured at different points in time, whereas a normal sequence does not necessarily have a temporal relationship between the elements.
From a picture, you get a sequence of pixels
From the picture, you get a sequence of pixels
But you can't change it.
Sequence.
And here it is again identified with the concept of temporal sequence, because that one can't change its data either.
If we change the sequence in the working dataset, we get a different picture.
If we change the temporal sequence... and we can't change it at all.
We need a clear example to show the difference.
Practical difference. So far, it looks like "walk" and "step".
But it cannot be changed.
Sequence.
And here it is again identified with the concept of temporal sequence, because it too cannot be changed.
If we change the sequence in the working dataset, we get a different picture.
If we change the temporal sequence... and we can't change it at all.
We need a clear example to show the difference.
Practical difference. So far, it looks like "walk" and "step".
The difference is the time dependence between the elements. It says. Not positional, but temporal.
Great IQ challenge, I didn't even expect it to be so hard to understand :)
just recently we were discussing who is a teacher in MO and something else funny was going on. Ah, how to get the probabilities on the output of the classifier ))
The difference is the time dependence between the elements. It says so right there. Not positional, but temporal.
Yes, I'm aware of that.
I'm curious about the practicalities. What it gives.
For example, a temporal sequence can be characterised as follows: until you finish the current step, you can't move to the next one. Until you convert the current time value, you can't move on to the next one. And you use the results of the previous step in the next one.
As in NS layers.
And in the sequence - the convolution goes in any direction: from left to right or from right to left, it doesn't care. It still summarises everything, but it puts the data in the right order.
This is probably an example.