Backpropagation in MQL4 Neural Network EA

Job finished

Execution time 2 days
Feedback from customer
It was a pleasure working with Mehmet. Nothing was too much trouble. Professional and punctual and understands the subject (Neural networks and backpropagation in my case) I would recommend him.

Specification

I need the backpropagation fixed in a Neural Network of an existing EA that will be used to take trades.


* Neural Network experience is essential * 
* Do not apply if you do not understand Backpropagation, Calculus (the chain rule), (Stochastic) Gradient descent and error functions *

95% of the code described below already exists.

The input features already exist in the code.

Neural network structure:
One input layer
Three hidden layers
One Output layer (2 to 4 outputs depending on activation)

REQUIREMENTS:
Backpropagation using stochastic gradient descent
Loss/Error function
Update gradients
Update weights and biases in file
The network must learn
The weights and biases gradients must not explode or vanish
possible regularisation and normalization adjustments
The MQL4 code must compile with no errors and no warnings (property strict) 

Clean existing code:
No libraries
No includes
No Errors
No Warnings
Clear well documented code
Variable names: use readable like trainingInputs[] rather than ti[] or x1[]

-------
The Existing code works like this:
Initialize:
Create random weights & biases in arrays
Write weights and biases to csv files

Train:
1) Load weights and biases from files into arrays (on each iteration)
2) Feed forward through NN (process input features)
3) Get a Buy or Sell signal (0 - 1) - EA takes a trade
4) Copy Feed Forward arrays to use at close of trade
(nothing happens until the trade closes)
5) When the trade closes, get the trade History Classify/Label the trade as buy/sell, profit/loss
6) Calculate error/cost function (using copied arrays)
7) Backpropagation (overwrite new adjusted weights and biases from updated arrays into files)
Repeat the process.

Trade:
Take trades using trained network
-------

Display on screen:
Trade quantity (considered as one labeled training example)
Last trade Ticket No.
Network output (predicted) eg. (0.2 | 0.8)
Actual (expected) output eg. ( 0 | 1) 
Trade type: Buy/Sell/Hold
Trade result: M15 - GBPUSD | win/loss (1.2% SL and TP = 2.6 * SL) (12 pips SL and 32 pips TP)
% Error over the epoch - Loss/Trade quantity (I want to see if the network is learning)

Write to file:
Write the cost/iteration No. to file stats.csv (new line for each with epoch No.)  so I can see or use the data to plot a graph in excel of the learn rate

I would like the code written in the same or similar style to mine.. (so I can understand the code and make any small changes in the future)

95% of the code already exists.

Timeframe: 2 days from start of job. Only take the job if and when you can start and complete in 2 days.
The budget is $150 - $200.
PAYMENT ON COMPLETION OF WORKING CODE ONLY.
Request the MQL4 file

Responded

1
Developer 1
Rating
(31)
Projects
56
21%
Arbitration
12
67% / 8%
Overdue
2
4%
Free
Similar orders
Description I need an very low latency MT5 Expert Advisor (EA) developed in MQL5 to automate TradingView alerts into MT5 trades for alerts set up done on trading view. The EA must work on both DEMO and LIVE accounts whichever will be attached to MT5 (XM, IC Markets and similar MT5 brokers) and be suitable for fast 1-minute timeframe scalping.End to End solution. Functional Requirements 1. TradingView Integration
Project Overview I am looking for an experienced MQL5 developer to build a custom, prop-firm-compliant trend-following Expert Advisor (EA) for MetaTrader 5 . This EA will be used on prop firm accounts (e.g., FTMO-style rules), so strict risk control and rule compliance are mandatory . This is NOT a grid, martingale, scalping, or recovery EA. The goal is consistency, rule compliance, and capital preservation , not
I am looking for an experienced MQL5 developer to build a professional MT5 software (indicator or semi-automated EA) for metals and major forex pairs. 📌 PLATFORM & MARKETS Platform: MetaTrader 5 Instruments: XAUUSD (Gold vs USD) XAGUSD (Silver vs USD) EURUSD GBPUSD USDJPY Trading styles: Scalping Intraday / short-term swing 🎯 MAIN OBJECTIVE I do NOT want an aggressive fully automated robot. I want a
I want to check if this indicator is repainting or not Whick mean the results of back testing is legit or not if anyone can help me to review it kindly to well to contact me i will be happy to work and go on long term work with anyone thanks
Specifications – Development of an MQL5 Expert Advisor (Reverse Engineering) Project context: I have access to a real trading history consisting of more than 500 trades executed over a period of approximately 3 years. These trades have been exported into a CSV file containing all available information, including date, time, symbol, order type, entry price, and exit price. Important: I do not have access to the
1.Sinyal Perdagangan : Sinyal beli: garis MACD utama memotong garis sinyal ke atas (macd_current>signal_current && macd_previous<signal_previous). Sinyal jual: garis MACD utama memotong garis sinyal ke bawah (macd_current<signal_current && macd_previous>signal_previous). Gambar di bawah menunjukkan kasus beli dan jual. 2. Posisi ditutup pada sinyal yang berlawanan: Posisi beli ditutup pada sinyal jual, dan posisi
specification High-Frequency Candle Momentum Scalper 1. Strategy Overview Core Logic: The EA identifies the current color of the active candle (Bullish or Bearish). Entry Trigger: It opens positions only after a specific duration of the candle has passed (e.g., after 30 seconds on a 1-minute candle) to confirm the direction. 2. Entry Logic (The "Half-Candle" Rule) Timeframe: M1 (Default, but adjustable). Time Filter
Greeting Im in need of a programmer that can help me convert from TOS to trading view? The script is available with me, kindly bid if it is what you can do for me Thanks
can you help me with I need an ATM strategy for NT8, here's the criteria: Forex trade entry 100,000 units with a starting SL of 70 pips. The following proft targets: 33 pips, 68, 125, 180. All targets exit 25,000 units each. As each target is hit, move SL to BE+5, then BE+35, then BE+70. So the SL's are fixed, not trailing. I can't figure this out on my platform
EA grid hunter 30 - 200 USD
1. Platform & Environment Platform: MetaTrader 5 (MT5 ONLY) Language: MQL5 Account type: ECN / Netting or Hedging Designed for broker rebate/commission return programs No DLLs, no external dependencies 2. Strategy Overview The EA is a high-frequency scalping Expert Advisor focused on maximizing the number of trades with minimal price movement, where the main source of profitability is broker rebate rather than market

Project information

Budget
150 - 200 USD
Deadline
from 1 to 3 day(s)