Interface: LtnTrainRequest

@kortexya/reasoninglayer

---

@kortexya/reasoninglayer / LTN / LtnTrainRequest

Interface: LtnTrainRequest

Defined in: src/types/ltn.ts:371

Request to train per-rule certainties (and, optionally, a neural predicate).

Example

const request: LtnTrainRequest = {
  rules: [{ individual: 'rex', sort: 'dog', membership: 0.9, certainty: 0.5 }],
  epochs: 100,
  learningRate: 0.05,
};

Properties

aggregator?

optional aggregator: LtnAggregator | null

Defined in: src/types/ltn.ts:375

KB-level aggregator. Absent ⇒ pMeanError(p = 2).

---

epochs?

optional epochs: number | null

Defined in: src/types/ltn.ts:380

Training epochs for the certainty optimiser (capped server-side).

Default Value

100

---

learningRate?

optional learningRate: number | null

Defined in: src/types/ltn.ts:385

SGD learning rate for the certainty update.

Default Value

0.05

---

predicate?

optional predicate: LtnPredicateTraining | null

Defined in: src/types/ltn.ts:387

Optional neural-predicate fit, persisted per tenant.

---

rules

rules: LtnRule[]

Defined in: src/types/ltn.ts:373

The rules whose certainties are trained to maximise SatAgg.