protocol

anomaly_detector_protocol

Protocol for machine learning anomaly detectors.

Availability:

logtalk_load(anomaly_detection_protocols(loader))

Author: Paulo Moura

Version: 1:0:0

Date: 2026-05-06

Compilation flags:

static

Dependencies:

(none)

Remarks:

(none)

Inherited public predicates:

(none)

Public predicates

learn/2

Learns an anomaly detector from the given dataset object.

Compilation flags:

static

Template:

learn(Dataset,AnomalyDetector)

Mode and number of proofs:

learn(+object_identifier,-compound) - one

---

learn/3

Learns an anomaly detector from the given dataset object using the specified options.

Compilation flags:

static

Template:

learn(Dataset,AnomalyDetector,Options)

Mode and number of proofs:

learn(+object_identifier,-compound,+list(compound)) - one

---

check_anomaly_detector/1

Checks that a learned anomaly detector term is structurally valid for the receiving implementation. Throws an exception when the term is not a valid anomaly detector representation.

Compilation flags:

static

Template:

check_anomaly_detector(AnomalyDetector)

Mode and number of proofs:

check_anomaly_detector(@compound) - one_or_error

Exceptions:

AnomalyDetector is a variable:

instantiation_error

AnomalyDetector is neither a variable nor a valid anomaly detector:

domain_error(anomaly_detector,AnomalyDetector)

---

valid_anomaly_detector/1

True when a learned anomaly detector term is structurally valid for the receiving implementation. Succeeds iff check_anomaly_detector/1 succeeds without throwing an exception.

Compilation flags:

static

Template:

valid_anomaly_detector(AnomalyDetector)

Mode and number of proofs:

valid_anomaly_detector(@compound) - zero_or_one

---

diagnostics/2

Returns diagnostics and metadata associated with a learned anomaly detector in a representation-independent way.

Compilation flags:

static

Template:

diagnostics(AnomalyDetector,Diagnostics)

Mode and number of proofs:

diagnostics(+compound,-list(compound)) - one

---

diagnostic/2

Tests or enumerates individual diagnostics metadata terms for a learned anomaly detector.

Compilation flags:

static

Template:

diagnostic(AnomalyDetector,Diagnostic)

Mode and number of proofs:

diagnostic(+compound,?compound) - zero_or_more

---

anomaly_detector_options/2

Returns the effective training options recorded in a learned anomaly detector.

Compilation flags:

static

Template:

anomaly_detector_options(AnomalyDetector,Options)

Mode and number of proofs:

anomaly_detector_options(+compound,-list(compound)) - one

---

predict/3

Predicts whether a new instance is normal or anomaly using the learned detector. The instance is a list of Attribute-Value pairs.

Compilation flags:

static

Template:

predict(AnomalyDetector,Instance,Prediction)

Mode and number of proofs:

predict(+compound,+list,-atom) - one

---

predict/4

Predicts whether a new instance is normal or anomaly using the learned detector and the specified options. The instance is a list of Attribute-Value pairs.

Compilation flags:

static

Template:

predict(AnomalyDetector,Instance,Prediction,Options)

Mode and number of proofs:

predict(+compound,+list,-atom,+list(compound)) - one

---

score/3

Computes an anomaly score in the interval [0.0, 1.0] for a new instance. Larger scores indicate more anomalous instances.

Compilation flags:

static

Template:

score(AnomalyDetector,Instance,Score)

Mode and number of proofs:

score(+compound,+list,-float) - one

---

score_all/3

Computes anomaly scores for all examples in a dataset and returns a list of Id-Class-Score triples sorted by descending score.

Compilation flags:

static

Template:

score_all(Dataset,AnomalyDetector,Scores)

Mode and number of proofs:

score_all(+object_identifier,+compound,-list) - one

---

export_to_clauses/4

Converts an anomaly detector into a list of predicate clauses. Functor is the functor for the generated predicate clauses. When exporting a serialized detector term, a noun such as detector or model is usually clearer than a verb such as detect.

Compilation flags:

static

Template:

export_to_clauses(Dataset,AnomalyDetector,Functor,Clauses)

Mode and number of proofs:

export_to_clauses(+object_identifier,+compound,+callable,-list(clause)) - one

---

export_to_file/4

Exports an anomaly detector to a file. Functor is the functor for the generated predicate clauses. When exporting a serialized detector term, a noun such as detector or model is usually clearer than a verb such as detect.

Compilation flags:

static

Template:

export_to_file(Dataset,AnomalyDetector,Functor,File)

Mode and number of proofs:

export_to_file(+object_identifier,+compound,+callable,+atom) - one

---

print_anomaly_detector/1

Prints an anomaly detector to the current output stream in a human-readable format.

Compilation flags:

static

Template:

print_anomaly_detector(AnomalyDetector)

Mode and number of proofs:

print_anomaly_detector(+compound) - one

---

Protected predicates

(none)

Private predicates

(none)

Operators

(none)

See also

anomaly_dataset_protocol, anomaly_detector_common, isolation_forest_anomaly_detector, knn_distance_anomaly_detector, lof_anomaly_detector