4088850/Warrior_EA
Watch
1
0
Fork
You've already forked Warrior_EA
 0
forked from animatedread/Warrior_EA
Code Pull requests Activity
Warrior_EA/Variables/Variables.mqh

20 lines
1.4 KiB
MQL5
Raw Permalink Normal View History

convert
2025-05-30 16:35:54 +02:00
//+------------------------------------------------------------------+
//| Warrior_EA |
//| AnimateDread |
//| |
//+------------------------------------------------------------------+
string eaName = "Warrior_EA";
string tableschema = "year INTEGER, month INTEGER, day INTEGER, dayOfWeek INTEGER, hour INTEGER, minutes INTEGER, pattern STRING, direction STRING, entryPrice DOUBLE, exitPrice DOUBLE, result STRING";
bool IsBacktesting = false;
feat: add weight scaling parameter to neuron initialization for improved training stability - Added optional `weighScale` parameter (default -1.0) to `CNeuronBase::Init` and `CLayer::CreateElement`. - Updated `CNeuronPool::Init` to use LeCun-uniform scaling (1/sqrt(window+1)) for its base initialization. - Updated `CNet::CNet` to use He-scaled initialization (sqrt(2/neurons)) for dense layers. - These changes enable more flexible and statistically sound weight initialization, matching the rationale used in OCL-based implementations, leading to better training stability and convergence.
2026-07-22 22:51:04 -04:00
//--- EnableITF/EnableSessionFilter/EnableNewsFilter/EnableRiskGuard moved to real inputs
//--- (Variables\Inputs.mqh) for consistency with every other filter's on/off toggle - see there.
refactor: merge AI topology preset into AI_CHOICE enum Eliminate the separate `AI_TOPOLOGY_PRESET` enum and input. Fold the topology presets directly into `AI_CHOICE` as new combined values (MLP_3L, MLP_4L, CONV_2L, LSTM_2L, HYBRID_2L) plus `AI_NONE`. Remove the `TopologyPreset` input variable and update default `AIType` assignments. Update the market description to reflect the simplified single‑selector interface. **Why:** Users previously had to choose an AI architecture and a topology preset separately. Now the UI shows one coherent selector that bundles architecture with its appropriate dense‑layer depth, reducing complexity and preventing mismatches.
2026-07-28 12:02:58 -04:00
bool EnablePAI = (AIType == MLP_3L || AIType == MLP_4L);
bool EnableCONV = (AIType == CONV_2L);
bool EnableLSTM = (AIType == LSTM_2L);
bool EnableHYBRID = (AIType == HYBRID_2L);
fix: correct array orientation and PReLU gradient backprop in hidden layers - Ensure `tick_volume` array is set as series in ADShorteningOfThrust.mq5 to prevent future-data leak in volume calculations. - Ensure `open` array is set as series in ADWyckoffFailedStructure.mq5 to prevent future-data leak in structure detection. - Add missing PReLU gradient scaling (multiply by 0.01 for negative outputs) in CPU_CalcHiddenGradient and DirectML shader to match expected derivative behavior across all backends.
2026-07-17 23:21:12 -04:00
//--- Unlike the Enable* flags above (fixed from inputs at file-load time), this one is only known at
//--- runtime - OnInit() sets it from CheckMarketDepthAvailability() before any signal is created, and
//--- OnDeinit() reads it back to decide whether MarketBookRelease() is needed. See
//--- Signals\SignalMarketDepth.mqh's class-level comment.
bool g_marketDepthAvailable = false;
convert
2025-05-30 16:35:54 +02:00
//+------------------------------------------------------------------+
Copy permalink