Menon et al. 2021 (ICLR), "Long-tail learning via logit adjustment": add
tau*log(prior_c) to each class logit inside the training gradient. Softmax
CE on adjusted logits is consistent for BALANCED error - the metric
checkpoint selection already ranks on - so the loss and the deploy decision
finally optimize the same thing.
The engine already computed a true softmax + categorical-CE gradient and
wrote it over the per-neuron sigmoid delta, so this is an offset added to
three logits in the two places that gradient is built (backProp scalar path
and backPropOCL). No backend, kernel or DLL change; the forward pass and
every inference path are untouched, which is the point - the network learns
to absorb the offset, so its raw argmax becomes the balanced-optimal
decision with nothing applied at inference.
Replaces rather than stacks. Minority replay is disabled while this is on,
and the post-hoc inference prior is forced off. Stacking is not a
theoretical worry: simulated on the measured 1118/1119/34298 distribution
in the weak-signal regime, plain CE collapses to Neutral (33.4% balanced,
Buy 0%), replay reaches 48.1%, logit adjustment 50.9% with better balance -
and BOTH together score 45.4% with Neutral recall at 0%, worse than either
alone. Buda et al. 2018 predicts exactly that.
Motivation from the six-chart run: every topology took one direction to
~50% recall and abandoned the other, the direction chosen arbitrarily (the
batch-norm control went Buy 1% / Sell 42%, the inverse of the other five).
One era in 1,301 cleared the per-class recall floor.
Fingerprinted conditionally, so the converged 60.7% models on disk keep
their filenames and stay loadable as the fallback.
Both builds compile 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Dividing a machine budget by the live chart count was wrong twice over.
The count is a snapshot taken when each net's pool is built, and charts
attach one at a time: five charts measured 10/6/5/4/4% of the same budget,
because the first only ever saw itself and the last saw all five. So the
earliest chart got several times the threads of the latest - skewing any
cross-topology comparison run on those charts, which is the exact thing
the setting existed to make fair. Nothing rebalanced afterwards either,
and rebalancing would mean tearing down a DLL context under a live trainer.
Both problems disappear once the answer stops depending on how many charts
are running. Each net now asks for a fixed 2 worker threads, converted to
the percentage the DLL wants from the detected core count.
Two is not a compromise: since the topology became data-derived the widest
dense layer is 64 units, so each ParallelFor has almost nothing to split
and per-dispatch overhead dominates. An MLP era cost ~66s at a wildly
oversubscribed 12 threads and ~80s at 1 thread - a 20% spread across a 12x
difference in thread count. Two per net also lands six concurrent charts
exactly on a 12-core box.
Removing the input costs nothing on the product side: a Market build has no
DLL tier at all, so it was already compiled out to a constant there and no
buyer could reach it.
Both builds compile 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Deriving the first layer's width left NeuronsReduction and MinNeuronsCount
behind as inputs calibrated for something that no longer exists. Against a
hand-picked 500-wide first layer "keep 30%, floor at 20" produced a genuine
funnel - 500 -> 150 -> 45. Against the derived 64 it degenerates to
64 -> 20 -> 20: the reduction factor stops mattering after one step, and
"minimum neurons per layer" silently becomes the width of every layer but
the first. Two knobs whose labels no longer describe what they do.
The taper now runs geometrically from the derived first-layer width down to
a final hidden layer sized off the output count, spread evenly over however
many layers the chosen AIType implies:
MLP_3L 64 -> 28 -> 12 -> 3 29,151 dense weights
MLP_4L 64 -> 37 -> 21 -> 12 -> 3 30,450
CONV/LSTM/HYBRID_2L 64 -> 12 -> 3 27,763
and it stays a funnel at the floor, where the old rule could not:
D1 (first layer floored to 16) 16 -> 14 -> 12 -> 3
Both inputs are removed. With the width derived there is no freedom left in
the taper, so keeping either would only let the user contradict the
derivation. The layer COUNT stays selectable, because it is bundled into
AIType alongside the conv/LSTM front-end - depth is an architecture choice,
not a data-derived quantity, and pairing them means the two cannot
contradict each other.
m_minNeuronsCount / m_neuronsReduction survive as frozen members: nothing
reads them to build a topology any more, but they hold positional slots in
the .cfg sidecar and the weights fingerprint, and changing either value
would re-key every model on disk for no behavioural reason.
The DB config fingerprint drops both terms.
Compiles 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
InitialNeurons was an input whose only defensible value depends on two
things the user cannot see when picking from a dropdown: how wide the input
vector ended up after feature selection, and how much in-sample data the
study period actually yields. Left to a hand-picked constant it was badly
wrong - 500 units against a 420-wide input is 210,500 weights, 72% of a
292,583-weight model, against ~36,500 training bars of which only ~2,236
are directional. That is 6.6 weights per training bar, and it EXPANDS a set
of highly correlated inputs rather than compressing them.
The symptom was already in the logs and had been read as a depth problem:
the shallowest topology consistently beat the deepest (perceptron 52.7%
balanced, hybrid 41.3%). Over-parameterization predicts that ordering just
as well as covariate shift does, and only one of the two had been addressed.
ComputeFirstLayerWidth() budgets roughly one first-layer weight per
in-sample bar. Measured across the configurations in use:
M15 10y -> 256 units, 129,071 weights, 0.73 per bar
H1 10y -> 64 units, 28,727 weights, 0.65 per bar
H4 10y -> 16 units, 7,559 weights, 0.68 per bar
Two design points that matter:
- It estimates in-sample bars from the STUDY PERIOD and timeframe, not
from Bars(). What is downloaded grows over a terminal's lifetime, and a
topology that widened as history filled in would re-key its own weights
file and discard a trained model.
- The result is snapped down to a coarse power-of-two ladder, so the
estimate would have to be wrong by ~2x to change the answer.
Every field it reads is already part of the weights-filename fingerprint,
so the derived value needs no fingerprint entry of its own. The public
setter is removed - it could only have been called after construction, and
would either be ignored or silently re-key the model mid-run.
Where the data cannot support even the floor (D1 over 10 years is under
2,000 bars) it now says so and names the fixes, rather than quietly
training a model with more weights than examples.
The DB config fingerprint drops the term too, which re-keys existing
pattern databases once - correct, since a model an order of magnitude
smaller should not inherit the old one's win-rate history.
Compiles 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Introduce Direct Feedback Alignment (DFA) backward pass with gradient clipping, feedback matrix initialization, and a dedicated backPropDfa method. Add optimizer snapshot/restore hooks (CaptureOptimizerSnapshot, RestoreOptimizerSnapshot, SetOptimizerForAllNeurons) to temporarily switch the entire network's optimizer for replay-only updates during pass 2, preserving the original optimizer state. Support all neuron types including dropout, deconv, LSTM, and softmax in the snapshot logic.
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.
Allow multiple AI models to be active simultaneously by switching from
a single AIType selection to individual boolean Enable flags. Also
simplify build tag by removing date prefix.
In AI/Network.mqh, return early from InitDirectML during
tester/optimization/forward runs to prevent agent-side file-lock
failures caused by rapid stop/restart cycles accessing DLL imports.
In Expert/ExpertSignalAIBase.mqh, add MathIsValidNumber checks in
CalibratedConfidenceMagnitude and SignaledConfidence to safely handle
NaN values, and refactor ShutdownChartCleanup to accept a preserve
flag, avoiding unnecessary chart purges during tester runs for faster
shutdowns. Also add m_purgeChartOnDestruct member.
In AI/NeuronDirectML.mqh, clean up a minor comment formatting issue.
Introduce a global boolean `g_signalsVisible` to control whether signal
objects are displayed across all timeframes or hidden entirely. When
enabled, chart arrows and restore objects are set to `OBJ_ALL_PERIODS`;
otherwise they use `OBJ_NO_PERIODS`, allowing signals to be shown or
hidden at runtime without losing saved state.
Add `ShouldTraceTradeRejections()` helper that returns true only when
running in the Strategy Tester, optimization, or forward testing modes.
Use it to print diagnostic messages when trades are rejected due to a
prohibition signal or when `OpenLongParams`/`OpenShortParams` fail to
produce valid stop/take-profit levels. This provides targeted debugging
output without cluttering live trading logs.
Introduce a custom OnTester() function to score backtest results
for genetic optimization, targeting smooth linear equity curves.
The score combines profit factor, recovery factor, Sharpe ratio,
and trade density, with a drawdown penalty.
Fixes a bug in the drawdown penalty where the percent value was
not converted to decimal before scaling, causing a near-zero
penalty. Also adjusts brace indentation for consistency.
Add MACD_FAST, MACD_SLOW, MACD_SIGNAL presets and Ichimoku Tenkan, Kijun, Senkou presets to InputEnums.mqh. All combinations are designed to satisfy the respective indicator's validation rules (fast < slow for MACD, Tenkan < Kijun < Senkou B for Ichimoku), eliminating init errors and allowing the auto-tuner to perturb settings independently.
Introduce VOTE_CLOSE_PRESETS enum with a Disabled option (value 101) that bypasses vote-driven position closing via arithmetic thresholding, removing the need for a separate boolean flag. This ensures positions exit only via stop-loss, take-profit, or trailing when disabled.
Removes standalone AI confidence parameters (MinAIConfidence, MinAIExitConfidence) and replaces them with unified Min_Vote_Open and Min_Vote_Close thresholds that apply to both AI and classic engines. Updates all code comments, report suggestions, and market descriptions accordingly, simplifying configuration and ensuring consistent vote requirements across entry and exit logic.
Add BeginVote/RevokeVote lifecycle hooks to ExpertSignalCustom and ExpertSignalAIBase.
Snapshot m_lastNonNeutralSignal before condition evaluation in Direction(), and restore
the snapshot if the vote is later discarded (e.g., Hybrid quorum shortfall).
Previously, a discarded vote still consumed the alternation gate, which could
permanently gate out valid signals until the opposite direction appeared.
BlendWeightsFrom now uses CObject::Type() to correctly identify neuron classes, avoiding undefined behavior when neurons are from the plain-CPU hierarchy (CNeuron, CNeuronConv, CNeuronPool, CNeuronLSTM). Weight blending for those legacy classes is also implemented.
The old RescanChartSignals ran the entire per-bar inference loop synchronously,
blocking the button-click handler for a potentially long duration on large lookbacks.
Replaced with StartChartSignalRescan (cheap setup) and AdvanceChartSignalRescan
(time-boxed slices) so the heavy work is drained from PollTraining's timer without
freezing the UI.
Introduce `RescanChartSignals()` method and `SIGNAL_RESCAN_LOOKBACK_BARS` define to allow operators to replace stale historical arrows (e.g., from years-old training runs) with fresh inferences from the currently deployed weights on recent bars. This prevents outdated signals from lingering on the chart and ensures the displayed set matches what a live re-render would produce.
PersistWeightsOnShutdown now returns early when m_inferenceOnly is true,
preventing the tester cache from being overwritten with untrained state.
InitNeuralNetwork compares modification timestamps of the production model
(FILE_COMMON) and the agent-local cache, re-seeding when the production
copy is newer. This ensures backtests always run the latest deployed
weights even when the cache file persists across runs. Also moved
LoadChartSignals() call to after the config fingerprint is appended,
so that persisted arrows are correctly keyed per configuration.
Replace fixed short-delay retries in CopyFileWithRetry and LoadNetWithRetry with exponential backoff (8 attempts, cap at 2s) to reliably handle transient file locks from AV/EDR or concurrent saves.
Change autosave trigger from a fixed 300-second wall-clock timer to firing on new bar close, reducing unnecessary overwrites and narrowing the collision window with backtest FileCopy operations.
Extract shared persistence logic into PersistDeployedModel() to guarantee consistency across all deploy paths (ladder, era-cap, stop, and manual). Add DeployNow() to let the panel button finalize the current best checkpoint as the live model, and RetrainDeployed() to revert deployment and resume training from the deployed weights without starting from scratch. This enables operator-controlled deployment while preserving online continual learning.
Implement a plateau detection mechanism that escalates through warm restart, gamma annealing, and eventual deployment when balanced accuracy stagnates for `PLATEAU_PATIENCE_ERAS`. Also add a compatibility shim for the removed `MinWR` input to preserve model filenames and `.cfg` layout.
Rename the original `CreateElement` with a defaulted `weighScale` parameter to `CreateElementScaled` and provide a proper virtual override that matches the base `CArrayObj::CreateElement` signature exactly. This ensures `CArrayObj::Load()` dispatches correctly, fixing a bug where every saved model load failed at the first layer. Update all call sites in `CNeuronBase::Init` and `CNeuronPool::Init`. Additionally, enhance error diagnostics in `CNet::Load` to distinguish between file truncation and code faults (such as the signature mismatch).
- In Network.mqh: Add upfront file size check to distinguish truncated files from backend allocation failures during model load, improving error diagnosis.
- In ExpertSignalAIBase.mqh: Remove redundant shadow net save on shutdown to avoid doubling shutdown cost and exceeding MT5's deinit budget, preventing abnormal termination and subsequent retrain.
- In Warrior_EA.mq5: Reduce training timer interval from 5s to 250ms to allow more frequent training cycles instead of sitting idle ~98% of the time.
Updated comments across ExpertSignalAIBase.mqh to explicitly state that the
compounded accuracy metric is a directional win-rate (Buy/Sell predictions only)
and that neutral/no-trade calls are excluded to avoid inflating the rate (since
neutral is the ~94% majority). The cumulative counters now only increment when
the prediction is directional, ensuring the panel reflects genuine trade quality
rather than overall label accuracy.
Split `PersistOnShutdown` into `PersistWeightsOnShutdown` (heavy weights save) and `ShutdownChartCleanup` (save arrows + purge chart). In `OnDeinit`, run panel destruction and per‑signal chart cleanup **before** the weight persistence, preventing leftover chart objects when the weight save stalls or faults past MT5's deinit budget.
Add CaptureWeights and RestoreWeights methods that snapshot every neuron's weights into host arrays (CArrayDouble per neuron) and restore them in-place via setWeights. This replaces the file-based SaveCheckpoint/LoadCheckpoint for the mid-run best-era rollback, because the file path re-creates neurons (CLayer+Init) which fails on the multithreaded CPU-DLL backend (CDirectMLMy/WarriorCPU.dll) that cannot allocate a second full set of neuron tensors while the live set exists. In-memory weight copy uses only getWeights/setWeights, already proven by the per-era shadow blend. Snapshots weights only (not Adam moments); the regression handler decays eta on restore and clips per-step deltas to prevent stale-moment overshoot. Snapshot is valid only within a single Train() run. Also adds HaveWeightSnapshot() query and the m_weightSnapshot / m_haveWeightSnapshot member variables.
- Guard CNet::Save to refuse writing a 0-layer network (prevents overwriting ~18MB model with empty stub)
- In CNet::Load and LoadCheckpoint, treat 0-layer files as load failure (older stubs still on disk)
- Introduce LOGIT_PRIOR_STRENGTH_PRESETS enum (0–100%) to control logit adjustment tau
- Prepare member variables and AdjustedSignalFromSoftmax for prior-corrected posterior at inference
- Ensure raw argmax scoring for recall/convergence remains unchanged; correction only affects live signal
Moved #resource directives for all custom indicators from IndicatorResources.mqh to Warrior_EA.mq5 to keep embedding logic in a single location and simplify build configuration. Updated comments to clarify MARKET vs. private build behaviour and path resolution.
Add `MA_TYPE_PRESETS` enum covering advanced (ALMA, DEMA, ZLEMA, T3, Kalman) and standard (SMA, EMA, SMMA, LWMA) moving averages. Integrate `maType` and `bestMaType` into `CADIndicatorTuner` struct, update flatten/unflatten routines, and bump `AD_TUNE_PARAM_COUNT` to 33. This allows the auto-tuner to search over MA type alongside period, improving feature discovery.
- Added ConfirmDestructiveAction() function that shows a warning MessageBox before executing destructive reset/delete operations.
- Used confirmation for "Reset" (AI weights) and "ResetDB" (database) actions to prevent accidental data loss.
- Moved "Report" button creation before the "Signals" button so that the two red (destructive) buttons appear adjacent at the bottom of the panel.
Replace single `m_pattern_0` weight with four confidence-tier weights (`m_pattern_0` through `m_pattern_3`) so that `UpdateSignalsWeights()` blends across multiple patterns like classic indicators. Previously, a single pattern caused the same win rate to be written to both the pattern weight and module weight, resulting in a quadratic derating (e.g., 70% win rate scored as 49 instead of 70). The new tiers bucket confidence into four equal bands between the minimum AI confidence and 1.0, with defaults 80/87/93/100. Added `ConfidenceTier()` and `PatternWeightForTier()` helpers, and changed default pattern count from 1 to 4.
- 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.
Remove verbose book references from input parameter comments in
Network.mqh for clarity. Add #ifndef guard around ENUM_OPTIMIZATION
to allow inclusion from multiple headers without redefinition.
Document the MQL5 Market DLL restriction in NeuronDirectML.mqh and
introduce WARRIOR_MARKET_BUILD macro to conditionally compile out
DirectML DLL imports for Market-compliant builds.
Replace old ATR_MULTIPLIER, THRESHOLDS_PRESET enums with new
STOP_LOSS_MODE, TAKE_PROFIT_MODE, AI_EXIT_MODE enums that support
ATR-based, intelligent confidence-scaled, and swing-anchored modes.
Also fix LSTM signal identity string.
Implement non-max suppression (NMS) to declutter signal visualizations by keeping only the first bar of each same-direction run, controlled by m_signalClusterWindow. Also replace blended accuracy with balanced accuracy (macro-recall) for checkpoint selection to avoid neutral bias, tracked via m_bestBalancedOos. This improves signal clarity and model deployment quality.
Introduce OVERSAMPLE_PARITY_FRACTION (0.7) to control minority class oversampling scaling, reducing low-quality directional calls by not fully replicating to parity. Add m_minSignalConfidence (0.5) to require a minimum softmax probability for live Buy/Sell orders, preventing firing on bare plurality (~0.34) and improving signal quality.
Introduce m_useSwingContext flag and FindConfirmedZigZagPivot method to compute normalized swing direction/magnitude/age features from the existing ADZigZag indicator. Only pivots that are at least m_swingConfirmationBars old are trusted, preventing lookahead bias. The SWING_SCAN_CAP_BARS macro limits backward scan depth. Default is off.
Audit turned up a real gap for a prop-firm-portfolio-manager use
case: nothing in this codebase watched for account-level daily-loss
or max-drawdown breaches - the single most common way a prop-firm
evaluation actually gets failed.
New Signals/SignalRiskGuard.mqh (CSignalRiskGuard), wired into the
exact same filter-composition chain as SignalNewsFilter/
SignalSessionFilter (CreateSignalWithRetry/AddFilterToSignal, no new
architecture). Vetoes new entries only (never closes existing
positions - a materially bigger behavior change, left to the
trader/EA's own SL/TP handling) once either MaxDailyLossPct or
MaxDrawdownPct (new RISK_LIMIT_PCT_PRESET inputs, both default
disabled) is breached. Peak equity and the current broker day's
starting balance persist to a small local per-symbol-per-magic state
file - peak equity in particular must survive a restart to mean
anything, otherwise a restart would silently reset drawdown tracking.
New RISK_LIMIT_PCT_PRESET enum (2/3/4/5/8/10/15/20%) rather than
reusing PERCENTAGE_PRESETS, which steps by 10 starting at 10 - too
coarse for prop-firm-style limits (commonly single-digit daily loss,
~8-10% max drawdown). Compiled clean (MetaEditor, 0 errors/0
warnings).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Price, time, volume, and volatility were already trained-model input
features; the real economic calendar (already used for the live
NewsFilter veto) is now an optional one too, reusing
System/NewsRelevance.mqh's symbol-relevance logic from the prior fix.
New EnableNews/NewsFeatureWindowMinutes inputs gate two features per
bar: minutes-since and minutes-until the nearest symbol-relevant
calendar event, impact-weighted. Deliberately limited to proximity +
impact, not actual-vs-forecast deviation - release schedules are
public knowledge ahead of time (not lookahead bias to use for a
historical training bar), but a release's actual outcome is not.
Wired identically to the existing EnableVolume/EnableTime/EnableATR
toggles: InitIndicators() accounts for the +2 neuron count,
BufferTempDataCompute() appends the two feature values, PAI/CONV/LSTM
all wired in Warrior_EA.mq5. Compiled clean (MetaEditor, 0 errors/0
warnings).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- Lowered Adam momentum parameter b1 from 0.9 to 0.8, shortening the effective memory window (~5 steps) to reduce multi-era bias streaks observed in training runs.
- Added FOCAL_GAMMA_PRESET enum and corresponding member variable m_focalGamma to apply focal loss modulation (Lin et al. 2017) on top of class-balance weighting, targeting the same streak issue by downweighting already-confident examples.
- Updated comments to document the rationale and experimental nature of both changes.
Replace the hardcoded `MAX_CLASS_SAMPLE_WEIGHT` (3.0) with a tunable member variable `m_maxClassSampleWeight`, controlled by the new `CLASS_SAMPLE_WEIGHT_PRESET` input enum. This allows adjusting the ceiling on rare-class sample weights to prevent the previously observed anti-correlated Buy/Sell recall whipsaw (where a high multiplier caused one era's gradients to overwrite another class's separability). Default is CSW_15 (1.5x), which is gentler than the old 3.0x; lower values down to 1.0x disable rebalancing to train on raw label distribution, while higher values (up to 3.0x) converge faster but risk instability. This tuning can now be done without recompiling.
- Removed TEST_HOLDOUT_PRESET enum and its associated member variables (m_testHoldoutPct, dTestForecast, m_testSamples) from ExpertSignalAIBase to simplify code and eliminate unused test slice logic.
- Added m_lastNonNeutralSignal member to track the last non-neutral signal during live inference, preventing LongCondition()/ShortCondition() from opening a second consecutive same-direction trade (which would be a false fire based on training patterns where valid reversals always alternate direction).
- This live-only mechanism does not affect historical training or backpropagation.
- 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.
Migrate all per-era classification counts, OOS confusion metrics, and training progress output from the legacy Comment() function to a dedicated StatusLabel object. This provides cleaner UI integration and avoids blocking the chart's normal info line during prolonged training cycles. A new include for StatusLabel.mqh has been added, and all related documentation comments updated accordingly.
- Added MAX_CLASS_SAMPLE_WEIGHT (3.0) to cap the sample weight multiplier, preventing anti-correlated Buy/Sell recall whipsaw observed when per-era ratio overwrites previous separability.
- Added MIN_OOS_CLASS_SAMPLES_FOR_GATE (10) to require a minimum number of true OOS samples before trusting class recall, avoiding degenerate false-convergence cases.
- Increased TRAIN_TIME_BUDGET_MS from 80 to 500 to improve throughput under MT5's custom event dispatch model (which determines actual pacing); trades UI responsiveness (~500ms lag) for roughly 6× more bars processed per event.
