Backpropagation in MQL4 Neural Network EA

작업 종료됨

실행 시간 2 일
고객의 피드백
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.

명시

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

응답함

1
개발자 1
등급
(32)
프로젝트
57
23%
중재
12
67% / 8%
기한 초과
2
4%
무료
비슷한 주문
Project Description I am looking for an experienced MQL5/MT5 Expert Advisor developer to develop an automated trading EA for XAUUSD on the M3 timeframe , running on an Exness account . The EA will automate a manual strategy based on SNR/GAP zones , using two setup types: Price Rejection Price Correction The EA should identify valid BUY/SELL setups around predefined SNR/GAP areas, apply configurable RSI, SMA, EMA and
I need an MT5 Expert Advisor for XAUUSD (Gold) running on an Exness account. STRATEGY LOGIC The exact entry and exit rules will be provided in writing before development starts. Please quote for a single rule-based strategy with clearly separated logic, so the rules can be adjusted later without rewriting the whole EA. RISK MANAGEMENT (this is the priority of the project) - Risk per trade as a percentage of account
Modification of Trade_Panel_7 7.05 Objective . I have this utility “Trade_Panel_7 7.05” with which I open and close positions. Please refer to attached “Trade Panel Modification.jpg”. It shows an input parameter “Volume Step”. This parameter has the initial value of 0.02 as shown. This feature needs to be amended. Present Status . Value of lot size is increased by this “Volume Step”. I have built a whole series of
Hello Traders, Have a trading strategy or idea you want to automate? I specialize exclusively in MQL5 development, helping traders turn their concepts into professional trading solutions. Custom Expert Advisors — automate your strategy and reduce manual execution Custom Indicators — transform your market ideas into powerful trading tools Fix & Debug — identify errors and get your existing code working properly
please share: Strategy description — entry/exit rules, indicators used, timeframe(s), and instrument(s) (a written explanation, screenshots, or an existing indicator/EA to reference all work) Risk management rules — position sizing method (fixed lot / % risk), stop loss / take profit logic, max drawdown or daily loss limits, and whether martingale/grid/hedging is involved Broker & account details — broker name
I need a unique grid trading system for XAUUSD that combines entry, controlled two-sided grid expansion, DCA (Dollar Cost Averaging) basket profit control, hedging. Unlike traditional grid EAs that only trade against price, this unique grid system should dynamically build positions in both directions based on market movement, allowing flexible adaptation to changing conditions ie the grid needs to dynamically move
I need an experienced MQL5 developer to create a fully automated MT5 Expert Advisor called Ayoub Gold EA , focused exclusively on XAUUSD (Gold) . Main requirements: Platform: MT5 / MQL5. Fully automated BUY and SELL trading on XAUUSD. Must support broker suffixes such as XAUUSD, XAUUSD.f and XAUUSDm. Trading strategy based mainly on Range Breakout with trend confirmation. EMA, ADX and ATR filters. London/New York
Mashiri 50 - 10000 USD
I need a custom MetaTrader 5 indicator designed specifically for XAUUSD gold trading. The indicator should identify potential buy and sell opportunities, display clear entry and exit signals on the chart, provide alerts, and help identify market trends and possible reversals
Looking for an experienced Sierra Chart ACSIL/C++ developer to customize an existing footprint chart. I need 3 things: 7-Day ATR – calculate and display a configurable 7-day ATR. Custom Footprint – modify my existing footprint chart to match my preferred layout/data display. Automatic LVN – detect and plot Low Volume Nodes automatically based on volume distribution. I already have a working footprint chart, so no
//———————————————————————————————————————————————————————————————————— struct S_MCAV { double matureSum; double totalSum; double value; void Init () { matureSum = 0.0; totalSum = 0.0; value = 0.5; } void AddContext (int ctx) { totalSum += 1.0; if (ctx == 1) matureSum += 1.0; } void ApplyDecay (double rate) { matureSum *= rate; totalSum *= rate; } void Update () {

프로젝트 정보

예산
150 - 200 USD
기한
에서 1  3 일