让神经网络自动推理物体关系，解智商题准确率达98%
Auto-Relational Reasoning
- 用神经网络自动建模物体间关系进行推理
- 无先验知识下解决智商题，准确率98.03%（对应132-144智商）
- 适合少样本或零样本问题，可拓展至多类任务
过去十年机器学习快速发展，但大模型已逼近性能瓶颈，呈现收益递减，且缺乏扎实的推理能力。通过融合机器学习的可扩展性与严格的逻辑推理，有望突破这些限制。本文提出一种自动化物体关系推理的理论框架，并将其与人工神经网络集成。我们对推理过程进行了形式化分析，并在实践中构建了融合推理与机器学习的新范式。该系统在无需任何问题先验知识的情况下，解决了智力测验题目，达到98.03%的解答率，对应人类智商的前1%分位，即132-144分。该结果受限于模型规模和运行设备的算力。未来结合先验知识与更大数据集，系统可推广至更广泛的问题类别，且天然支持少样本或零样本求解。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。