DeepAI AI Chat
Log In Sign Up

Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability

by   Qinglai Wei, et al.
University of the Chinese Academy of Sciences

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


page 4

page 5

page 8

page 9

page 10

page 11

page 13

page 14


Learning to reason over visual objects

A core component of human intelligence is the ability to identify abstra...

DAReN: A Collaborative Approach Towards Reasoning And Disentangling

Computational learning approaches to solving visual reasoning tests, suc...

Unsupervised Abstract Reasoning for Raven's Problem Matrices

Raven's Progressive Matrices (RPM) is highly correlated with human intel...

Neural Abstract Reasoner

Abstract reasoning and logic inference are difficult problems for neural...

Neural-Symbolic Recommendation with Graph-Enhanced Information

The recommendation system is not only a problem of inductive statistics ...

Explanatory Paradigms in Neural Networks

In this article, we present a leap-forward expansion to the study of exp...

The minimal computational substrate of fluid intelligence

The quantification of cognitive powers rests on identifying a behavioura...

Code Repositories


Implementations of RS-CNN and RS-TRAN

view repo