# Efficient predicate invention using shared "NeMuS"

## TL;DR

This paper introduces Amao, a cognitive agent framework that employs a Neural Multi-Space graph structure to efficiently invent predicates and support inductive learning, including recursive hypotheses, within a constrained logical language.

## Contribution

It presents a novel predicate invention method using shared NeMuS graphs that enhances inductive logic programming with neural weights and supports recursive hypothesis learning.

## Key findings

- Supports recursive hypothesis learning.
- Uses neural weights to guide predicate invention.
- Restricts hypothesis shape with language biases.

## Abstract

Amao is a cognitive agent framework that tackles the invention of predicates with a different strategy as compared to recent advances in Inductive Logic Programming (ILP) approaches like Meta-Intepretive Learning (MIL) technique. It uses a Neural Multi-Space (NeMuS) graph structure to anti-unify atoms from the Herbrand base, which passes in the inductive momentum check. Inductive Clause Learning (ICL), as it is called, is extended here by using the weights of logical components, already present in NeMuS, to support inductive learning by expanding clause candidates with anti-unified atoms. An efficient invention mechanism is achieved, including the learning of recursive hypotheses, while restricting the shape of the hypothesis by adding bias definitions or idiosyncrasies of the language.