Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability
This work addresses the problem of enhancing AI's abstract reasoning capabilities for researchers in machine learning, though it appears incremental as it builds on existing RPM benchmarks and methods.
The paper tackles the challenge of improving neural networks' ability to solve abstract reasoning problems, specifically RAVEN's progressive matrices, by incorporating felicitous inductive bias and a multi-viewpoint with multi-evaluation strategy, achieving elegant solutions without extra metadata or specific backbones.
Great endeavors have been made to study AI's ability in abstract reasoning, along with which different versions of RAVEN's progressive matrices (RPM) are proposed as benchmarks. Previous works give inkling that without sophisticated design or extra meta-data containing semantic information, neural networks may still be indecisive in making decisions regarding RPM problems, after relentless training. Evidenced by thorough experiments and ablation studies, we showcase that end-to-end neural networks embodied with felicitous inductive bias, intentionally design or serendipitously match, can solve RPM problems elegantly, without the augment of any extra meta-data or preferences of any specific backbone. Our work also reveals that multi-viewpoint with multi-evaluation is a key learning strategy for successful reasoning. Finally, potential explanations for the failure of connectionist models in generalization are provided. We hope that these results will serve as inspections of AI's ability beyond perception and toward abstract reasoning. Source code can be found in https://github.com/QinglaiWeiCASIA/RavenSolver.