Machine learning in trading: theory, models, practice and algo-trading - page 3410
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
Whoever is curious will be.
The video is about an attempt to extract additional information from leaves, after building a gradient bousting model, to improve the model in various ways. However, in the middle of the second part our roads with the author of the video diverged.
Usually does not lead to new knowledge, but as a method of correction can be used. Within some unknown limits. Sometimes it gives nothing at all.
Usually it does not lead to new knowledge, but it can be used as a method of correction. Within some unknown limits. Sometimes it does nothing at all.
My vision is like this, a sample is a Lego-like constructor - there is a set of different parts, a model is an attempt to assemble something interesting out of these parts without instructions - to write your own instructions. So, leaves here will be in a role of the enlarged components - some blocks successfully moulded, as the manufacturer of the constructor initially intended, for example the figure of the man is collected successfully, though with defects. Such successful constructions - per cent 10 in the model turns out - all the rest - a stray imagination, having nothing to do with the original instructions.
So, collecting such semi-defective leaves from different models, you can collect more successful blocks, which are stacked in accordance with the instruction.
Re-learning from these leaves is the task of distributing "parts" to all the models in a way that provides variety but eliminates similarity.
In the end should get more elements from the original idea of the manufacturer of the constructor. It is clear that the constructor is often delivered with missing parts and the perfect model can not be assembled, but what can be done.
So it's hard to get more information out of one model, but you can try to get it out of a hundred.
As for the video, their idea of reducing the weight of leaves - well, it won't work properly... You have to do some tricky calibration of leaf weight - I can't do it yet. Building a new bousting model on leaves is the best option I have tested so far. Ideally, I'd like to try neuronics on one hidden layer, but I'm not sure it will be fast.
Neural network on paiten on tensorflow library on google machine on eur=usd API mt4 mt5 output?
Neural network on paiten on tensorflow library on google machine on eur=usd API mt4 mt5 output?
You are difficult to understand - what do you want?
My vision is like this, the selection is a Lego-like constructor - there is a set of different parts, the model is an attempt to collect something interesting from these parts without instructions - to write your own instructions. So, leaves here will be in a role of the enlarged components - some blocks successfully moulded, as the manufacturer of the constructor initially intended, for example the figure of the man is collected successfully, though with defects. Such successful constructions - per cent of 10 per cent in the model - all the rest - a stray imagination, having nothing in common with the original instruction.
So, collecting such semi-defective leaves from different models, you can collect more successful blocks, which are stacked in accordance with the instructions.
Repeated learning from these leaves is the challenge of distributing "parts" to all the models in a way that provides variety but eliminates similarity.
In the end should get more elements from the original idea of the manufacturer of the constructor. It is clear that the constructor is often delivered with missing parts and it is impossible to build a perfect model, but what can be done.
So it is difficult to get more information out of one model, but you can try to get it out of a hundred.
As for the video, their idea of reducing the weight of leaves - well, it won't work properly... You have to do some tricky calibration of leaf weight - I can't do it yet. Building a new bousting model on leaves is the best option I have tested so far. Ideally, I'd like to try neuronics on one hidden layer, but I'm not sure it will be fast.
You just need to find a pattern that makes it work in a non-random way. When that happens, you know immediately. But before that you have to try a lot of different things to have an opinion. Some people are lucky to get into the stream quickly.
.
Is there any way to apply these approaches to regular trades? You know, like crossing averages.
It's hard to understand you. What do you want?
Why does Elon Musk think AI is more dangerous than a nuclear bomb?
Bard:
Ilon Musk thinks AI is more dangerous than a nuclear bomb for several reasons:
1. Uncontrolled proliferation:
2. Potentially limitless power:
3- Unpredictability:
4. Speed of development:
5. Comparison to other dangerous technologies:
It's important to note that not all experts agree with Musk.
Nevertheless, Musk's views are worthy of consideration,
Chat Gpt:
Ilon Musk has raised concerns about artificial intelligence (AI) in several interviews and tweets. He believes that the development of AI without proper control and oversight could lead to serious consequences, including the possibility of intelligent systems that could decide to enslave or destroy humanity.
Musk has also raised concerns about the development of AI in the military sphere, warning of the possibility of autonomous military systems that could make vital decisions without human oversight.
He is calling for governments and society as a whole to take the regulation and control of AI development more seriously in order to minimise the risks associated with its use.
Overall, Ilon Musk's concerns about AI relate to the potential threat he sees in the possibility of highly evolved systems capable of operating independently of human control and moral constraints.