Deep learning methods for abstract visual reasoning: A survey on raven's progressive matrices
M Małkiński, J Mańdziuk - arXiv preprint arXiv:2201.12382, 2022 - arxiv.org
Abstract visual reasoning (AVR) domain encompasses problems solving which requires the
ability to reason about relations among entities present in a given scene. While humans …
ability to reason about relations among entities present in a given scene. While humans …
A review of emerging research directions in abstract visual reasoning
M Małkiński, J Mańdziuk - Information Fusion, 2023 - Elsevier
Abstract Abstract Visual Reasoning (AVR) problems are commonly used to approximate
human intelligence. They test the ability of applying previously gained knowledge …
human intelligence. They test the ability of applying previously gained knowledge …
Abstract spatial-temporal reasoning via probabilistic abduction and execution
Spatial-temporal reasoning is a challenging task in Artificial Intelligence (AI) due to its
demanding but unique nature: a theoretic requirement on representing and reasoning …
demanding but unique nature: a theoretic requirement on representing and reasoning …
Are deep neural networks SMARTer than second graders?
Recent times have witnessed an increasing number of applications of deep neural networks
towards solving tasks that require superior cognitive abilities, eg, playing Go, generating art …
towards solving tasks that require superior cognitive abilities, eg, playing Go, generating art …
Hierarchical ConViT with attention-based relational reasoner for visual analogical reasoning
Abstract Raven's Progressive Matrices (RPMs) have been widely used to evaluate the visual
reasoning ability of humans. To tackle the challenges of visual perception and logic …
reasoning ability of humans. To tackle the challenges of visual perception and logic …
Scale-localized abstract reasoning
We consider the abstract relational reasoning task, which is commonly used as an
intelligence test. Since some patterns have spatial rationales, while others are only …
intelligence test. Since some patterns have spatial rationales, while others are only …
In-context analogical reasoning with pre-trained language models
Analogical reasoning is a fundamental capacity of human cognition that allows us to reason
abstractly about novel situations by relating them to past experiences. While it is thought to …
abstractly about novel situations by relating them to past experiences. While it is thought to …
Interactive visual reasoning under uncertainty
One of the fundamental cognitive abilities of humans is to quickly resolve uncertainty by
generating hypotheses and testing them via active trials. Encountering a novel phenomenon …
generating hypotheses and testing them via active trials. Encountering a novel phenomenon …
Learning to reason over visual objects
A core component of human intelligence is the ability to identify abstract patterns inherent in
complex, high-dimensional perceptual data, as exemplified by visual reasoning tasks such …
complex, high-dimensional perceptual data, as exemplified by visual reasoning tasks such …
Neural prediction errors enable analogical visual reasoning in human standard intelligence tests
Deep neural networks have long been criticized for lacking the ability to perform analogical
visual reasoning. Here, we propose a neural network model to solve Raven's Progressive …
visual reasoning. Here, we propose a neural network model to solve Raven's Progressive …