Neural network
Also see Market etiquette or the rules of good manners in a minefield
Your questions cover such a large area of knowledge and research that no one can explain on the fingers.
I recommend reading books on neural networks, to get the basics right. Then do your own research in this area. The innermost secrets
of cooking NN will not be shared.
The questions of interest are:
1. As far as I understand each neuron of the network is the same function... but I don't understand how the same function can produce different values when the same data comes in...
2. How to normalize quotes without knowing their minimum and maximum?
1. Depends on the initial weights, it's not always possible to find a global minimum with a single training even in a few thousand epochs.
2. You can take the price difference and determine the maximum difference if you use linear normalization. If you use non-linear, the learning will be better, as some say, although I haven't found much difference for me personally. Maybe a little faster learning, but there is more hassle with normalisation.
1. Depends on the initial weights, it is not always possible to find a global minimum with a single training even in several thousand epochs.
2. You can take the price difference and determine the maximum difference if you use linear normalisation. If you use non-linear, the learning will be better, as some say, although I haven't found much difference for me personally. Maybe a little faster learning, but there's more hassle with normalisation.
1. I understand that the initial weight, but how do I get it? I'd like to have an example of neuron, at least...
1. I know it's the initial weight, but how do I get it? I'd like an example of a neuron at least...
Initial weights are usually chosen randomly. Read "Neurocomputer Science: Theory and Practice", a well known book by Wasserman, where everything is quite well described. There is also a book titled "Basic concepts of neural networks" by Robert Callan which describes basic features of networks, there is a description of probabilistic neural networks. And if you want to dive into this world for years, you cannot do without Simon Heikin:)
Dear guru, please help me to understand neural networks as long as I try, I still can not understand how they work, how to make them, how to train them, if it is not difficult, please show simple examples explaining what and how....
I am interested in the following questions:
1. As far as I understood each neuron of the network is the same function... but I don't understand how one and the same function with the same data can give different values...
2. How to normalise quotes without knowing their minimum and maximum???
I would like more graphical information and at least simple examples of neural network with a built-in learning mechanism...
Thanks in advance hope for your help...
the answer to the first question:
The answer to the second question is in the same book on page 111.
Book by Stanislav Osovsky "Neural networks for information processing".
Normally structured code
Thank you very much sorry not many comments but I will try to figure it out....
Thank you very much sorry not many comments but I'll try to figure it out....
Trader does not really need to understand the inner workings of NS. For him it is a black box with inputs and outputs. There are a lot of ready-made networks in the public domain, including on this site - just type "neural networks" in the search box. One of the latest publications, for example - Predictor based on a self-learning neural network. The main problem in using NS is the choice of what data to input and train, how to prepare this data, what is the structure and size of the network, etc. For example, we take the already mentioned network, try to train it the way Yezhov and Shumsky did (see Neurocomputing and its application in economics and business, I recommend)... And we end up with a flop. There may be many reasons for this. This is where the trader's work starts, to get intuition for what may have changed since then (or what the authors are not telling ;-) ), and what to change in the settings and input data.
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use
Dear guru, please help me to understand neural networks as long as I try, I still can not understand how they work, how to make them, how to train them, if it is not difficult, please show simple examples explaining what and how....
I am interested in the following questions:
1. As far as I understood each neuron of the network is the same function... but I don't understand how one and the same function with the same data can give different values...
2. How to normalise quotes without knowing their minimum and maximum???
I would like more graphical information and at least simple examples of neural network with a built-in learning mechanism...
Thanks in advance hope for your help...