Reported: on deinit the panel and status label go, the signal arrows stay.
Two independent causes, both fixed here.
1. It was partly deliberate. ShutdownChartCleanup carried a second
behaviour selected by a `preserveChartArrows` flag derived from the
deinit reason: on RECOMPILE / PARAMETERS / CHARTCHANGE / TEMPLATE the
arrows were left on the chart on purpose, to avoid a reload flicker.
That branch IS the reported symptom, an operator cannot tell it apart
from a cleanup that failed, and it was outright wrong whenever the
reload changed the config - REASON_PARAMETERS means exactly that, and
the preserved arrows then belonged to a model the chart no longer
runs, with nothing marking them stale. It is gone, along with the flag
and m_purgeChartOnDestruct. One path now: persist, clear, restore on
the next attach.
2. Whatever remains was unfalsifiable. PurgeChart was a single
ObjectsDeleteAll(prefix) whose return value was discarded, with no
caller ever looking at the chart again - so "the arrows are still
there" and "the arrows were never there" produced identical evidence,
which is why the report survived three sessions. It now verifies:
after the bulk delete it walks the OBJ_ARROW-typed list (a handful of
objects, not the whole chart), deletes any surviving WarSig_ by name,
and says so. Costs one typed scan when the bulk delete works, which is
the normal case; names the root cause when it does not.
Every failure mode of SaveChartSignals was also silent - it returned void
and had three bare early returns. It returns bool now, logs the open
error with the filename, and the shutdown purge is CONDITIONAL on it: for
a converged model the chart objects are the only copy of its signal
history (nothing redraws them - the renderer runs per training era and a
deployed model has none left), so a chart left littered because the disk
write failed beats a clean chart bought by destroying the history. Either
way the log now says which happened.
Also states the user's rule once, where arrows come back rather than
across InitNeuralNetwork's several exits: no weights loaded for this
config => clear the sidecar and start visually clean. A fresh run must
not inherit calls it never made, and the first save would otherwise adopt
them (the sidecar is rebuilt by scanning the chart).
Compiles 0 errors / 0 warnings, standard and Market. Needs redeploy.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
- Moves CLayer neuron construction to AI/Impl/Layer.mqh to keep Network.mqh clean
- Unifies four previously duplicated architecture initialisation blocks (MLP/CONV/LSTM/HYBRID) into a single shared function
- Eliminates risk of behavioural drift where one architecture missed a setter, causing mismatched feature sets or targets
Three defects found by reading the 2026-08-01 training logs, all of which
only became visible because the relabel made the numbers mean something.
1. A STALE ENUM TRAINED FOUR MODELS ON THE WRONG TARGET.
`OnInit: trade settings snapshot - SL_Mode=1 TP_Mode=-101`
-101 was TP_PREV_SWING, deleted from TAKE_PROFIT_MODE on 2026-07-31 in
7eb48f5. MetaTrader does not validate a saved enum input against the
enum's current members, so charts saved before that kept the old
integer. BarrierMultiples()'s `if(tpMult <= 0.0) tpMult = slMult;`
then quietly turned it into a 1:1 barrier, and all four topologies
trained ~250 eras against a strategy nobody selected - while the log
reported "target 1.00*ATR" as though it were configured.
Since the relabel these two inputs ARE the label definition, so this
is not a bad trade setting, it is a wrong dataset. ValidateBarrier-
Inputs() now refuses to start (INIT_FAILED + Alert + an explicit fix)
on any value that is not an enum member. Members are enumerated rather
than range-checked because both enums are sparse and carry negative
sentinels, so no min/max test can tell a legal value from a deleted
one - which is the entire failure mode. The fallback survives as
belt-and-braces but now announces itself: a fallback that cannot say
it fired is indistinguishable from correct behaviour.
2. THE DEPLOYABILITY FLOOR BECAME MATHEMATICALLY UNREACHABLE.
`tradeableOK` required `dirPrecPct >= baseRatePct`, where baseRatePct
is Buy+Sell as a share of all bars. At the old exact-pivot target that
was ~6%, so "beat the base rate" read as "beat chance" and the test
looked sound. Triple-barrier labels put it at ~83%, so the gate now
demanded 83% directional precision - impossible by construction.
Observed live: all four topologies cycling "PLATEAU stage 3 ... nothing
safe to deploy" at a perfectly healthy 43-45% precision, with no
checkpoint able to ship however good it got.
Replaced with ZERO-SKILL precision, max(Buy,Sell)/allBars: exactly the
score of the degenerate always-call-one-direction model this floor
exists to reject. Correct at any base rate - ~43% on the current
labels, ~3% on the old rare-pivot ones. The era line now prints
"(chance N%, edge +Mpp)" beside the selection score, because 44%
precision is excellent against a 3% chance level and worthless against
a 43% one, and reading the first as the second is what made tonight's
run look better than it was.
3. THE HORIZON IGNORED THE BARRIER GEOMETRY.
ComputeBarrierHorizonBars() returned the median ZigZag leg, which
measures how long a ~1 ATR move takes and says nothing about how long
the CONFIGURED barrier needs. First-passage time out of [-m,+k] scales
with m*k, so a 1:3 barrier takes ~3x as long as 1:1; the unscaled
horizon would have timed out most 1:3 trades and pushed Neutral
straight back up, re-creating the imbalance the relabel removes.
Now multiplied by slMult*tpMult, calibrated against a real measurement
rather than assumed: the accidental 1:1 run resolved at horizon 12 with
only 16.7% timeouts, so the swing median is the right scale at m*k=1.
Verifiable, not just asserted: the prebuild now counts barriers that
ended on the VERTICAL barrier and reports them as a share of Neutral.
Neutral conflates "timed out" with "stopped out" and only the first
indicts the horizon.
Both builds compile 0 errors / 0 warnings. Forces a retrain - correcting
TP_Mode re-keys the fingerprint (|TB:1:-101 -> |TB:1:3), which is right:
no existing model was trained on the intended target.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Every removal below is FINGERPRINT-NEUTRAL by construction: each retired
input is pinned to the exact value it already shipped with, so running
models keep their filenames and resume rather than restarting at era 0.
Verified field by field against BuildConfigFingerprint.
Removed as inputs, kept as pinned constants (the value was never a
preference the user had a basis to change):
- OutputNeuronsCount. The regression head predicts a continuous quantity
the triple-barrier label does not contain; the target is an EVENT, so
the right output is its probability. The regression code paths stay
implemented and dormant - they cost nothing and removing them would
touch every scoring path at once.
- MinRecall. A safety floor, not a preference, and the only direction a
user can move it is the harmful one: raising it past what the config
reaches yields NO model, not a better one (observed repeatedly at 60).
- SwingConfirmationBars. Stopped gating the labels with the relabel, but
is STILL load-bearing for the swing-context input features - it is the
ZigZag repainting embargo, and without it those 9 features read a leg
the live bar could not have had yet. Pinned, not deleted.
- MaxErasPerRun (runaway backstop, never reached in a healthy run),
FreezePriorCalibration (unanswerable by a user; near-balanced labels
make the priors stable anyway), VerboseMode (developer view, joins
DebuggingMode), MACD/Ichimoku periods x6 (both indicators ship
disabled, and as optimizer dimensions they are pure overfitting
surface - the AI auto-tuner is the supported way to move them).
- SignalClusterWindow -> 3, no longer an input. Barrier labels make
consecutive setups real, which argued for 0; it is not 0 because on D1+
a 6-bar window spans over a week and two arrows a day apart on a
weekly-scale move are one event. 3 splits it correctly by timeframe.
- EnableOnlineLearning -> ON. Adapting to a changing market is what keeps
a months-attached model from going stale, and the rolling-accuracy
freeze is what makes it safe. See the caveat noted in the handoff: it
had not been forward-tested on a live feed when this became default.
Removed entirely:
- Intraday Time Filter (5 inputs + Signals/SignalITF.mqh). Two of its
five inputs were raw BITMASKS, which is an implementation detail
exposed as a control. The job is covered three times over by things
that are declarative or that learn: the session filter, the
time-of-day/day-of-week input features (the network discovers which
hours are good rather than being told), and the journal's time buckets.
- Market Depth Filter (5 inputs + Signals/SignalMarketDepth.mqh, plus
its OnInit probe and OnDeinit release). It needs real level-2 data
that this broker - and most retail MT5 brokers - do not provide, so
the module has never once executed against real data. Shipping four
tuning dropdowns for an untested path is worse than shipping nothing:
the only users who could enable it would be its first-ever testers,
live. If DOM returns it should be a FEATURE fed to the network, not a
rule-based veto with hand-tuned thresholds - imbalance is data.
- IndicatorTuneTrials, replaced by ComputeTuneTrialBudget(). The useful
budget depends on how many parameters are actually being searched,
which depends on which features are enabled - so one number meant
wildly different things run to run. The shipped 32 was ~10 candidates
per dimension against one enabled indicator (wasteful: each costs
GA_SEEDS full training runs) and under one per dimension against all
nine (blind). Now population ~ 4 x active dimensions, clamped [8,64],
with CADIndicatorTuner::ActiveDimensions() defined immediately above
PerturbRandom() so the two cannot drift apart.
- Six orphaned enums (TUNE_TRIALS_PRESET, DOM_*, ENTRY_HOUR_OF_DAY,
TIME_FILTER_DAY_OF_WEEK), 81 lines.
Other UX:
- SL_ATR_x1 / TP_ATR_x3 now carry the "(classic)" default marker every
other preset enum in the file already used. Nothing in the SL/TP
dropdowns previously told a user which pair was the shipped default -
which matters far more since the relabel, because those two define the
labels and changing either forces a retrain.
- Neural Network section moved directly ABOVE AI Input Features: choose
the architecture, then choose what it sees. NN Optimizer / Performance
stays last - the Adam/Sgd inputs are declared in AI/Network.mqh and
render immediately after that divider.
- News feature + window moved to the end of the AI feature list, below
Wyckoff Bar Inversion.
- Dropped "(0-100)" from Min vote to open - it is an enum, not a number.
Both builds compile 0 errors / 0 warnings. No retrain forced.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The 31:1 class imbalance was self-inflicted by the TARGET, not a property
of the market. Labelling only the exact bar where a ZigZag pivot confirms
gave Buy 1164 / Sell 1164 / Neutral 35841, and every correction mechanism
this codebase accumulated sits downstream of that one choice: the
logit-adjusted loss and its range cap, the prior EMA, the +-3.0 output-bias
seed, balanced-accuracy-then-precision selection with its coverage floor,
the recall floor and its catch-22, the alternation gate, NMS, and the four
oversampling designs that collapsed before them.
The reference this engine is built on (references/neuronetworksbook.pdf
ch. 3.1/3.3) also uses ZigZag, but targets the DIRECTION TO THE NEXT
EXTREMUM on every bar - ~50/50 by construction, with no imbalance to
correct at all. It never had this problem because it never asked "is this
the pivot bar".
Labels are now the triple barrier (Lopez de Prado ch. 3), using the EA's
OWN SL_Mode/TP_Mode: does a trade opened at this bar's close reach its
target before its stop, within a horizon. Buy = long resolves, Sell =
short resolves, Neutral = neither. Consequences:
- dir-precision in the era line stops being a proxy and becomes the win
rate of the strategy under its own exit rules.
- Expected balance ~25/25/50 at the shipped 1:3 (gambler's ruin), i.e.
~2:1 instead of 31:1. Measured and logged at the end of the prebuild.
- Spread is charged on both legs, so it is a NET win rate.
- Intrabar ambiguity resolves to the STOP. OHLC cannot order two touches
inside one bar and the optimistic reading is how a backtested edge
becomes a live loss.
ZigZag stays as input features (EnableSwingContext) and now also supplies
the vertical barrier: the horizon is the median confirmed leg length,
snapped to a coarse ladder. Derived, not configured, and deliberately kept
out of the filename fingerprint - a filename keyed on a measured quantity
orphans a trained model the moment the measurement moves.
Removed, because the premise died with the old target:
- the alternation gate. Correct for pivot labels (a ZigZag cannot emit two
same-type pivots in a row, so a repeat was provably a false fire), and
wrong for barrier labels, which answer each bar independently. It also
took its worst consequence with it: a one-sided model previously got ONE
trade per backtest, a hard blocker on marketplace validation.
- SignalClusterWindow now defaults off - it de-duplicated repeats that are
now real trades. Kept as an opt-in display control.
- LABEL_WINDOW_BARS, the pivot-widening pass, ConfirmedZigZagLabel.
- the era-0 output-bias seed now needs a genuinely dominant class (0.70)
rather than 0.40; at ~50% Neutral a +-3.0 seed is a distortion, not a
correction.
Also fixed, both found while wiring the above:
1. RefreshConvergedSignal sized its buffers from a date delta
(Bars(sym, period, dtStudied, TimeCurrent())). dtStudied is a training
watermark; in the tester it is loaded from a live-chart save AHEAD of
the simulated date, so the interval inverted, Bars() returned ~0, and
the buffer came out at exactly m_historyBars - deep enough for the OHLC
window and far too shallow for the Donchian-50 / 20-bar-return / SMA
extension behind it. Inference silently computed DIFFERENT features
from the ones training learned on, live as well as in the tester. Now
sized from what the feature builder actually needs.
2. The barrier horizon is resolved on the deployed path too. A deployed
model never enters Train(), so it never reached the prebuild, and
OnlineLearnStep reads the horizon as its confirmation delay - left at
the fallback it would have backpropped bars whose barriers had not
resolved. Silent lookahead in the one place that writes to a live model.
SL_Mode/TP_Mode join the weights fingerprint: they define the labels now,
so a model trained at 1:3 must never be silently reused at 1:1. This
re-keys every pre-existing model by design - none were trained on this task.
Inference census extended with the vote gate. LongCondition/ShortCondition
open with a readiness check the refresh counters never see; in the tester it
reduces to "the seeded _optcache.nnw must have LOADED", and if it did not,
every vote is hard-zeroed while the model still answers Buy. The old three
counters would have read that as "the model says Neutral" - false, and a
completely different fix. This is the leading candidate for the
zero-direction backtest and the census can now name it in one run.
Both builds compile 0 errors / 0 warnings. Forces a full retrain.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The imbalance section offered nine controls for one job. Audited against the
code, five of them did not do what their names said at the shipped defaults:
AILogitPriorStrength DEAD - Inference.mqh's post-hoc prior early-returns
whenever the adjusted loss is on, which is default.
OversampleParity DEAD in training - Training.mqh gated the replay loop
on !useLogitAdjustedLoss (correctly, citing Buda et
al. 2018). Live only in the online-learning path.
EnableMinorityReplay DEAD as replay. It survived ONLY as a focal-gamma
damper - "replay minority bars through pass-2
oversampling" was a focal-loss switch.
ConstrainReplay DEAD as a cap; it only chose damper 0.125 vs 0.25.
UseStaticPrior An exact duplicate of FreezePriorCalibration - the two
were OR'd together in the single place either is read.
So they were not five mechanisms fighting; they were one mechanism plus eight
knobs that mostly described machinery that no longer ran. That is worse than
a real conflict, because the log agreed with the names: the label-cache line
printed "reps up to 28x (90% parity) (seeding era 0's class-balance
oversampling)" on every run, describing an oversampling pass that had been
switched off. It is fixed here too - it cost this session a wrong diagnosis.
The one genuine redundancy was focal loss, running at gamma*0.125 alongside
the adjusted loss: two corrections on the same axis, the exact stacking
failure this file already cited Buda et al. for in two other places, damped
by a replay flag whose replay path was itself dead. Removed rather than
re-tuned. The plateau ladder is unaffected - its escape is the learning-rate
warm restart; the gamma anneal beside it only ever stepped toward zero.
WHAT REMAINS is logit-adjusted loss (Menon et al. 2021) plus a prior freeze:
LogitAdjustTau 0 = off; replaces the separate EnableLogitAdjusted-
Loss boolean, since a strength dial where 0 already
means off does not need an on/off switch beside it.
FreezePriorCalibration unchanged.
It is the only one of the six corrections with a consistency guarantee, and
it is consistent for exactly the balanced-error metric checkpoint selection
already ranks on - so the loss and the deploy decision optimize one thing.
The online continual-learning path keeps its own alpha-balanced focal weight,
now as constants pinned to the removed inputs' shipped defaults, so its
behaviour is unchanged. It legitimately needs its own correction:
ApplyLogitAdjustment() only runs inside a training run, so a deployed model
that was reloaded carries no logit offsets and would otherwise stream 31:1
data into itself uncorrected.
The weights-filename fingerprint is BYTE-IDENTICAL. The focal slot was a
double fed to a %d conversion and had always emitted a literal 0; the |MR:
segment is written as the constant its shipped defaults produced. Dropping
either would have re-keyed every model and forced a from-scratch retrain of
the one topology currently converged and trading.
Also removed as orphans: FOCAL_GAMMA_PRESET, MAX_OVERSAMPLE_REPLICAS,
OVERSAMPLE_PARITY_FRACTION, PLATEAU_GAMMA_STEP, and the now-unreachable
"neutralized by prior correction" diagnostic.
Both builds compile 0 errors, 0 warnings. No retrain forced.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Completes the derived-topology work. Three inputs removed.
AIType loses its depth suffix - AI_MLP/AI_CONV/AI_LSTM/AI_HYBRID, five
entries instead of eight. Depth is now derived from the two endpoints
the taper already has to connect (derived first-layer width, output-tied
final width) at a 2x per-layer compression target, clamped [2..5].
Asking a user to pick a layer count while the code derives the widths
those layers taper between was asking for half a decision: at 64 units
tapering to 12, four layers compress by 1.4x per step and five by 1.3x,
so the extra depth bought no abstraction. On the shipping H1/10y default
the derivation lands on 3 layers - the depth that actually won Run 2.
StudyPeriods removed. There is no case for training on less data than
the broker provides at a ~6% directional base rate; the honest
generalization read comes from the OOS holdout, not from withholding
history. Training now starts at the earliest available bar, floored by
MinTrainYear, which answers a different question (excluding dubious
pre-history) and stays.
That required closing the hazard the old code documented: the capacity
budget now MEASURES the symbol's real bar count, and a topology derived
from a measurement would widen as history downloads. Both ends are now
pinned. Every derived value left the weights-filename fingerprint -
keying a filename on a measured quantity means the EA looks for a file
that does not exist, starts from era 0 and orphans a trained model,
silently, because a missing cache is the normal first-run state. The
shape lives in the .cfg instead, where LoadAndCompare now ADOPTS the
four derived fields rather than diffing them; a mismatch there would
discard a fully-trained model over nothing the user did. Two fields
appended to the .cfg for the conv/LSTM stages, length-guarded on read
because FileReadInteger past EOF returns 0 with no error.
ForceHiddenLayers, a compile-time constant like DebuggingMode, pins
depth for diagnostic comparisons. It joins the fingerprint only when
non-zero, so forced depths get their own files - sequential comparisons
only, not simultaneous from one .ex5.
Derived shape, H1/10y defaults (21 features x 20 bars): first layer 64,
3 dense, 8 conv filters, 16 LSTM units. The LSTM block halves from
~58k to ~28k weights.
Both builds compile 0 errors, 0 warnings. Re-keys existing models.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Same defect the first-layer width had before 2026-07-29: both were
inputs whose defaults were fixed constants picked with no reference to
the input they sit on, which is the only thing that decides whether
either number is sane.
The conv layer is a per-bar projection - AddConvStage sets
window = step = one bar's features - so its filter count should be read
against the per-bar feature count. Sixteen filters COMPRESSED a
50-feature configuration 3x but EXPANDED a minimal 4-feature one 4x, and
the expanding case adds parameters below every learnable layer without
adding information. Now derived as half the per-bar feature count,
snapped down a power-of-two ladder.
The LSTM stage was the bigger miss. Its weight count is exactly
4*H*(H+inputs+1) (CNeuronLSTMOCL::SetInputs) and AddLstmStage feeds it
the whole flattened vector, so the shipped 32 units against a 540-wide
input is ~73k weights - more than DOUBLE the entire derived dense taper
it feeds. It was the one stage the capacity budget never covered, which
is why deriving the dense stack alone did not stop LSTM and HYBRID from
being over-parameterized. Now solved from the same
one-weight-per-in-sample-bar budget the first layer spends.
Factored EstimatedInSampleBars() out of ComputeFirstLayerWidth so all
three decisions spend one budget rather than each guessing at the
training-set size separately. Both new values are assigned alongside the
first-layer width, before the fingerprint that hashes them, and are
functions of inputs already in that hash - so they need no entry of
their own, and the same reasoning removes them from the DB config key.
Both builds compile 0 errors, 0 warnings. Re-keys existing models.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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.
