Warrior_EA/Signals/SignalHYBRID.mqh

58 lines
3.1 KiB
MQL5
Raw Permalink Normal View History

fix(ai): drop the conv pooling stage - it reduced across filters, not time FeedForwardConv emits POSITION-MAJOR output, matrix_o[out + window_out * i], so one bar's window_out filter responses are contiguous and consecutive bars sit window_out apart. Both pooling implementations (FeedForwardProof and CPU_FeedForwardProof) slide FLAT over that buffer - pos = i * step, reducing `window` CONSECUTIVE elements. On a position-major layout those neighbours are different FILTERS of the same bar, never one filter across time. At the shipped 3/2 the pool computed max(bar0_f0, bar0_f1, bar0_f2), then max(bar0_f2, bar0_f3, bar0_f4), with every 8th window straddling a bar boundary. So it collapsed unrelated feature detectors into whichever fired hardest, passed gradient to that winner only, and halved the feature map while doing it - all below every learnable layer, where nothing above can recover it. The removed inputs' own labels ("3 Bars") show time-axis pooling was the intent throughout. Measured cost: CONV sat pinned at ~40% balanced accuracy for 510 eras with Sell recall 0%, while plain MLPs on the same data reached 57-61%. HYBRID, which also carried this stage, came second-worst of the batch-norm group. Not fixable in the topology: pooling one filter across time needs a stride of window_out BETWEEN samples within a window, which a consecutive-window kernel cannot express at any window/step. That needs a stride-aware kernel in Network.cl + WarriorCPU.cpp + WarriorDML.cpp and a DLL rebuild, and is only worth doing if a conv front-end earns its place without downsampling first - with 20 sliding positions there is little to gain by halving them. ConvPoolWindow/ConvPoolStep and their enums are removed with it, along with the |CP: fingerprint term added earlier today. Both builds compile 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 19:28:44 -04:00
//+------------------------------------------------------------------+
//| Warrior_EA |
//| AnimateDread |
//| |
//+------------------------------------------------------------------+
#include "..\Expert\ExpertSignalAIBase.mqh"
// wizard description start
//+------------------------------------------------------------------+
//| Description of the class |
//| Title=Signals of indicator 'CNN-LSTM AI' |
//| Type=SignalAdvanced |
//| Name=CNN-LSTM AI |
//| ShortName=HYB |
//| Class=CSignalHYBRID |
//| Page=signal_hybrid |
//+------------------------------------------------------------------+
// wizard description end
//+------------------------------------------------------------------+
//| Class CSignalHYBRID. |
//| Purpose: a single fused CNN-LSTM signal that stacks Conv+Pool |
//| layers before the LSTM layer, then the shared dense taper. |
//| The base AI voting path still applies, so this module trades as |
//| one coherent signal instead of three loosely synchronized ones. |
//+------------------------------------------------------------------+
class CSignalHYBRID : public CExpertSignalAIBase
{
protected:
virtual bool AddCustomLayers(CArrayObj *topology) override;
virtual ENUM_ACTIVATION HiddenLayerActivation(void) override { return TANH; }
public:
CSignalHYBRID(void);
virtual bool InitIndicators(CIndicators *indicators) override;
};
//+------------------------------------------------------------------+
//| Constructor |
//+------------------------------------------------------------------+
CSignalHYBRID::CSignalHYBRID(void)
{
SetIdentity("Hybrid", "HYB");
}
//+------------------------------------------------------------------+
//| Create indicators and bootstrap/load the network. |
//+------------------------------------------------------------------+
bool CSignalHYBRID::InitIndicators(CIndicators *indicators)
{
return InitNeuralNetwork(indicators);
}
//+------------------------------------------------------------------+
//| Conv + Pool front-end followed by an LSTM sequence layer. This |
//| matches the standalone CONV front-end exactly, then adds LSTM. |
//+------------------------------------------------------------------+
bool CSignalHYBRID::AddCustomLayers(CArrayObj *topology)
{
refactor: compose topologies from named stages; drop dead code DRY - topology construction --------------------------- CSignalCONV and CSignalHYBRID each built the Conv+Pool front-end from scratch; CSignalLSTM and CSignalHYBRID each built the LSTM stage from scratch. The duplicates had already drifted: HYBRID guarded the LSTM step with MathMax(1, historyBars/2), CSignalLSTM divided unguarded, so a historyBars of 1 gave two different steps for what is documented as the same layer. Extracted AddConvPoolStage() and AddLstmStage() onto CExpertSignalAIBase. The three overrides are now compositions: CONV = AddConvPoolStage LSTM = AddLstmStage HYBRID = AddConvPoolStage && AddLstmStage HYBRID's "matches the standalone CONV front-end exactly, then adds LSTM" is enforced by construction instead of by comment. Took the guarded step for both. Also fixed a descriptor leak the duplicates shared: on a failed topology.Add() the CLayerDescription was neither owned by the array nor deleted. Dead code --------- - CNet::SaveCheckpoint / CNet::LoadCheckpoint (123 lines). Superseded by the in-memory CaptureWeights/RestoreWeights pair; Network.mqh:1312 already said so ("This replaces the file-based SaveCheckpoint/LoadCheckpoint"). Zero call sites - every remaining mention was a comment. The five comments that referenced them have been reworded rather than left dangling. - CExpertSignalCustom::CheckForDuplicateTrade / FindLastTradeIndex / UpdateTradeStatusAndExit: declared, never defined anywhere, never called. They only made it look as though duplicate-trade detection existed. Compiles 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 00:38:05 -04:00
//--- "the standalone CONV front-end exactly, then adds LSTM" is now enforced by construction:
//--- both stages are the same code CSignalCONV and CSignalLSTM run.
fix(ai): drop the conv pooling stage - it reduced across filters, not time FeedForwardConv emits POSITION-MAJOR output, matrix_o[out + window_out * i], so one bar's window_out filter responses are contiguous and consecutive bars sit window_out apart. Both pooling implementations (FeedForwardProof and CPU_FeedForwardProof) slide FLAT over that buffer - pos = i * step, reducing `window` CONSECUTIVE elements. On a position-major layout those neighbours are different FILTERS of the same bar, never one filter across time. At the shipped 3/2 the pool computed max(bar0_f0, bar0_f1, bar0_f2), then max(bar0_f2, bar0_f3, bar0_f4), with every 8th window straddling a bar boundary. So it collapsed unrelated feature detectors into whichever fired hardest, passed gradient to that winner only, and halved the feature map while doing it - all below every learnable layer, where nothing above can recover it. The removed inputs' own labels ("3 Bars") show time-axis pooling was the intent throughout. Measured cost: CONV sat pinned at ~40% balanced accuracy for 510 eras with Sell recall 0%, while plain MLPs on the same data reached 57-61%. HYBRID, which also carried this stage, came second-worst of the batch-norm group. Not fixable in the topology: pooling one filter across time needs a stride of window_out BETWEEN samples within a window, which a consecutive-window kernel cannot express at any window/step. That needs a stride-aware kernel in Network.cl + WarriorCPU.cpp + WarriorDML.cpp and a DLL rebuild, and is only worth doing if a conv front-end earns its place without downsampling first - with 20 sliding positions there is little to gain by halving them. ConvPoolWindow/ConvPoolStep and their enums are removed with it, along with the |CP: fingerprint term added earlier today. Both builds compile 0 errors, 0 warnings. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-29 19:28:44 -04:00
return AddConvStage(topology) && AddLstmStage(topology);
}
//+------------------------------------------------------------------+