Auto-Relational Reasoning

TL;DR

This paper introduces a theoretical framework combining machine learning with formal reasoning to enhance AI's problem-solving abilities, demonstrated by a system achieving high IQ scores without prior knowledge.

Contribution

It presents a novel integration of reasoning and neural networks, enabling automated object-relational reasoning and solving IQ problems without prior knowledge.

Findings

Achieved 98.03% success rate on IQ problems

System performance limited by model size and hardware

Potential for generalization with more data and prior knowledge

Abstract

Background & Objectives: In the last decade, Machine learning research has grown rapidly, but large models are reaching their soft limits demonstrating diminishing returns and still lack solid reasoning abilities. These limits could be surpassed through synergistic combination of Machine Learning scalability and rigid reasoning. Methods: In this work, we propose a theoretical framework for reasoning through object-relations in an automated manner integrated with Artificial Neural Networks. We present a formal analysis of the Reasoning, and we show the theory in practice through a paradigm integrating Reasoning and Machine Learning. Results: This paradigm is a system that solves Intelligence Quotient problems without any prior knowledge of the problem. Our system achieves 98.03% solving rate corresponding to the top 1% percentile or 132-144 iq score. This result is only limited by the small size of the model and the processing capabilities of the machine it run on. Conclusions: With the integration of prior knowledge in the system and the expansion of the dataset, the system can be generalized to solve a large category of problems. The functionality of the system inherently favors the solution of such problems in few-shot or zero-shot attempts.