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
(32)
Projects
57
23%
Arbitration
12
67% / 8%
Overdue
2
4%
Free
Similar orders
Title: MT5 Forex Trading Robot Development I need a MetaTrader 5 (MT5) Expert Advisor (EA) for automated Forex trading. Requirements: 1. The robot must be fully automated and capable of opening and closing trades without manual intervention. 2. Compatible with MetaTrader 5 (MT5). 3. Adjustable lot size, Stop Loss, and Take Profit settings. 4. Built-in risk management based on account balance. 5. Ability to trade
Sierra Chart Alerts to MT5 via Webhook (Alert Manager File Version) Objective: Create a Custom Study (ACSIL / C++) that monitors alerts from the Alert Manager file and forwards any valid alert directly to MT5 via an HTTP POST (Webhook) in JSON format. Additional Note: The study should allow adding any modifications in the future and provide clear insights into the alert points in Sierra Chart. 1. Data Flow Diagram
ART 1: NUMBER OF TRADES ALLOWED IN ONE DIRECTION: Maximum number of trades in one direction = ------------------------------ ------------------------------ ------------------------------ -------------- par PART 2 PARTIAL CLOSURE OF STOPLOSS: Total STOPLOSS =------ Pips 1a: Percentage of Stoploss =--% 1b Percentage of Lot size =--% 2a: Percentage oe of Lot size =--% f Stoploss =--% 2b
MT5 Expert Advisor (EA) Acquisition Request – Proven XAUUSD Martingale / Grid EA I am looking to purchase a fully developed, actively traded, and proven MT5 Expert Advisor for XAUUSD (Gold) that uses Martingale, Grid, Averaging, Recovery, or Hybrid Recovery techniques. Mandatory Verification Requirement To be considered, please provide: - MT5 Investor Password (Read-Only Access) for verification - Account Number /
Looking to buy profitable MT4/MT5 Expert Advisors (EAs). Requirements: • Fully automated • 6+ months backtest • 100+ trades • No martingale or grid systems Send: • Backtest report • Max drawdown • Markets traded • Brief strategy summary Only original EAs developed by you. Long-term collaboration available
Live chart [ expert is not executing trades on xauusd ] , Deleting Existing Parameter not in use , Live Chart Adjustments Only , No Need to Change anything else , expert will be live testing Throughout
Prepare expert for xauusd live chart [ expert is not executing trades on xauusd ] . Deletion and cleaning code . Trailing Stop Rule to follow the given method . Live Chart Only
MT5 EA Developer for Structured ICT/SMC Market Logic Requirements Specification: I need an MT5 Expert Advisor only in MQL5. No indicator, no script, no DLL, and no external API. The EA must be built on a rule-based ICT/SMC-style framework with objective, backtestable logic. I am not looking for social-media-style ICT/SMC interpretation. I need a developer who can convert trading concepts into clear coding rules. The
Szukam doświadczonego programisty do stworzenia dedykowanego doradcy eksperckiego (EA) do tradingu. Programista powinien posiadać solidną wiedzę z zakresu MT5, logiki strategii, wskaźników, zarządzania ryzykiem i backtestingu. Doświadczenie w tworzeniu niezawodnych i profesjonalnych robotów handlowych będzie dodatkowym atutem. Proszę o kontakt, jeśli zrealizowałeś już podobne projekty. wszystkie szczeguły podam w
I’m looking for an experienced MetaTrader 4 (MT4) developer to analyze, repair, and live-test an existing .EX4 Expert Advisor. Project Details Existing file: GannMadeEasy_pro.ex4 Platform: MetaTrader 4 Issue: EA is not loading properly on charts in newer MT4 builds Goal: Make the EA fully functional and compatible with current MT4 versions Requirements The developer must: Analyze the existing EX4 file Identify

Project information

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