- Evgeniy Scherbina
- Versione: 2.5
- Aggiornato: 3 aprile 2023
- Attivazioni: 25
Fast Neurons is a neural strategy which is ready for fully automated trading with the following symbols: AUDUSD, EURUSD, GBPUSD, USDCAD, USDCHF, and USDJPY.
The main advantage of this advisor is that it uses techniques of the renowned Reinforcement Learning (RL). It is a promising direction of maching learning, which has been steadily gaining popularity in recent years. For example, the famous chatbot "ChatGPT" leverages the power of Reinforcement Learning. Unlike traditional methods of machine learning, a neural network in Reinforcement Learning does not know results of trades beforehand so it has to study the market by receiving rewards and penalties. This is a very important advantage of this technique of machine learning for Forex, because the advisor has learned to adapt to the quickly changing market conditions.
I am going to add the method of continued learning to the advisor in one of the updates, so that the advisor can continue learning while trading. The expectation is that the advisor will be able to adapt better to the specific trading conditions of your broker.
Start the advisor on one chart. Regardless of your current chart, the advisor always trades all its symbols at the same time.
You can start the advisor Fast Neurons on a chart of any symbol and any timeframe. Regardless of your current chart, the advisor analyzes data of monthly, weekly and daily charts for all its symbols at the same time.
- Suffix >> it can be handy for those who have different symbols with different suffixes in their terminal. Most users can leave this field empty.
- Volume >> either a fixed volume per trade (ex: 0.02) or a percent of available equity (ex: 0.015%). The advisor prints the actual volume in the "Experts" tab upon start or timeframe change. If your account does not use USD as the deposit currency (that is, euro, yuan, AUD, etc.), make sure it calculates a volume correctly or use a fixed volume.
- Same signal max >> a maximum number of trades while a signal repeat on one symbol. A new day is a new trade if the signal repeats.
- Same signal range >> a signal range on one symbol. Counting trades for the property "same signal max" is done within a signal range.
I must say that at the beginning it seemed negative, but after a month it returned positive, it uses a network system. For the record, I use the .3 model