The Path to Autonomous Learners

TL;DR

This paper proposes a hybrid model combining ontologies, knowledge graphs, and Logic Neural Networks to enable autonomous knowledge acquisition and domain extension in intelligent systems.

Contribution

It introduces a novel hybrid architecture for autonomous learning that integrates ontologies, reasoning, and neural networks for knowledge expansion.

Findings

System can enrich existing knowledge with new data.

Model extends knowledge to new domains.

Demonstrates effective reasoning over knowledge graphs.

Abstract

In this paper, we present a new theoretical approach for enabling domain knowledge acquisition by intelligent systems. We introduce a hybrid model that starts with minimal input knowledge in the form of an upper ontology of concepts, stores and reasons over this knowledge through a knowledge graph database and learns new information through a Logic Neural Network. We study the behavior of this architecture when handling new data and show that the final system is capable of enriching its current knowledge as well as extending it to new domains.