Using neural networks in trading - page 4
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
if it's no secret, why would you want to divide by zero
Not me, the terminal swears and stops the EA, which finishes the network in real time. There is no unsupervised division anywhere, I control it everywhere. So I'm learning one pair at a time.
That's it, if anything is unclear, please ask. Lines drawn manually based on the bottom indicator, assumed open
It came true. It was the EURNZD.
yep, but I'll keep an eye on the topic....
First window: The ideal entry into a long position (buy) is in the direction of the green and blue waves upwards. Entry can also be made when only the green wave is directed upwards, in which case one cannot expect any great movement of the instrument in terms of amplitude. Accordingly, the opposite will be true for short positions (selling).
The second window. Readings of the neural network working with the live channels.
The third window. Orange is also the EURUSD quote itself (that you see on your trading terminals). This window, we have left for displaying of the wave, created on the information, that has not passed the above mentioned filters of urgency - it is a green wave. Nevertheless, this information has a huge weight and this window serves to confirm the correctness of the readings of the neural network (second window).
:) a little tips about dividing by zero, when building a neural network I faced a small condition if = 0, then the value is assigned 0.00000000001 and divided, the final result will still be at the maximum, but the condition is fulfilled normally
First window:
Second window.
Third window.
All you have shown is the performance of the neural network on historical data. The results on the historical data are not interesting as you will be trading on future data.
Show how it will work on future data.
A neural network is essentially an intelligent computer (intelligence + feelings)
What does it need feelings for?
Very much needed. Without feelings, there is no intelligence. Suppose we created a robot capable of seeing and recognising objects, hearing and understanding speech, moving its arms and legs, etc. Turn on the ON button and ... Question to all. What would a robot do after we turn it on?