Modeling Cross-Cultural Performance on the Visual Oddity Task

Lovett, Andrew; Lockwood, Kate; Forbus, Kenneth D.

doi:10.1007/978-3-540-87601-4_27

Cited by 7 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the simplest case, two sketches can be compared by feeding their representations into SME. More complicated tasks that have been performed using CogSketch and its predecessors include everyday physical reasoning problems (Klenk, Forbus, Tomai, Kim, & Kyckelhahn, 2005) and a visual oddity task (Lovett, Lockwood, & Forbus, 2008).…”

Section: Sketch Understandingmentioning

confidence: 99%

Solving Geometric Analogy Problems Through Two‐Stage Analogical Mapping

Lovett¹,

Tomai²,

Forbus³

et al. 2009

Cognitive Science

Self Cite

View full text Add to dashboard Cite

Evans' 1968 ANALOGY system was the first computer model of analogy. This paper demonstrates that the structure mapping model of analogy, when combined with high-level visual processing and qualitative representations, can solve the same kinds of geometric analogy problems as were solved by ANALOGY. Importantly, the bulk of the computations are not particular to the model of this task but are general purpose: We use our existing sketch understanding system, CogSketch, to compute visual structure that is used by our existing analogical matcher, Structure Mapping Engine (SME). We show how SME can be used to facilitate high-level visual matching, proposing a role for structural alignment in mental rotation. We show how second-order analogies over differences computed via analogies between pictures provide a more elegant model of the geometric analogy task. We compare our model against human data on a set of problems, showing that the model aligns well with both the answers chosen by people and the reaction times required to choose the answers.

show abstract

Section: Sketch Understandingmentioning

confidence: 99%

Solving Geometric Analogy Problems Through Two‐Stage Analogical Mapping

Lovett¹,

Tomai²,

Forbus³

et al. 2009

Cognitive Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The prior art approach utilizing the computational model explored how the presence of particular concepts makes a riddle difficult for humans. That model’s accuracy was found to be significantly correlated with human performance 18 , 19 , As the concepts present in our generated dataset directly correspond to the ones from the original experiment, we perform a similar comparison based on the detailed accuracies reported for the Munduruku participants 17 . Figure 4c depicts the human performance for the riddles ranked by increasing difficulty level for humans along with the accuracy for the most biologically plausible of our models: a saccadic network with spiking neurons ( N = 128).…”

Section: Resultsmentioning

confidence: 97%

“…An approach to study the visual oddity task by resorting to a computational model was proposed in refs. 18 , 19 , where the authors used the frames from the original work 17 to first generate representations based on glyphs, while separately considering properties of edges, shapes, lines, points, etc. The model then adopts a structure-mapping engine to find the commonality across the frames.…”

Section: Introductionmentioning

confidence: 99%

On the visual analytic intelligence of neural networks

Woźniak,

Jónsson,

Cherubini

et al. 2023

Nat Commun

View full text Add to dashboard Cite

Visual oddity task was conceived to study universal ethnic-independent analytic intelligence of humans from a perspective of comprehension of spatial concepts. Advancements in artificial intelligence led to important breakthroughs, yet excelling at such abstract tasks remains challenging. Current approaches typically resort to non-biologically-plausible architectures with ever-growing models consuming substantially more energy than the brain. Motivated by the brain’s efficiency and reasoning capabilities, we present a biologically inspired system that receives inputs from synthetic eye movements – reminiscent of saccades, and processes them with neuronal units incorporating dynamics of neocortical neurons. We introduce a procedurally generated visual oddity dataset to train an architecture extending conventional relational networks and our proposed system. We demonstrate that both approaches are capable of abstract problem-solving at high accuracy, and we uncover that both share the same essential underlying mechanism of reasoning in seemingly unrelated aspects of their architectures. Finally, we show that the biologically inspired network achieves superior accuracy, learns faster and requires fewer parameters than the conventional network.

show abstract

“…In the odd-one-out (O 3 ) problems, the set of images is already extended with a panel that breaks the pattern -the odd one. O 3 problems have been widely studied from both cognitive and computational angles [6,[50][51][52][53] and commonly appear in human puzzles [5]. In fact, the challenge of identifying an odd element in a set of objects has been recognised as fundamental not only to humans, but also to other animals [54,55].…”

Section: Odd-one-outmentioning

confidence: 99%

A Review of Emerging Research Directions in Abstract Visual Reasoning

Małkiński¹,

Mańdziuk²

2022

Preprint

View full text Add to dashboard Cite

Visual Reasoning (AVR) problems are commonly used to approximate human intelligence. They test the ability of applying previously gained knowledge, experience and skills in a completely new setting, which makes them particularly well-suited for this task. Recently, the AVR problems have become popular as a proxy to study machine intelligence, which has led to emergence of new distinct types of problems and multiple benchmark sets. In this work we review this emerging AVR research and propose a taxonomy to categorise the AVR tasks along 5 dimensions: input shapes, hidden rules, target task, cognitive function, and main challenge. The perspective taken in this survey allows to characterise AVR problems with respect to their shared and distinct properties, provides a unified view on the existing approaches for solving AVR tasks, shows how the AVR problems relate to practical applications, and outlines promising directions for future work. One of them refers to the observation that in the machine learning literature different tasks are considered in isolation, which is in the stark contrast with the way the AVR tasks are used to measure human intelligence, where multiple types of problems are combined within a single IQ test.

show abstract

Modeling Cross-Cultural Performance on the Visual Oddity Task

Cited by 7 publications

References 18 publications

Solving Geometric Analogy Problems Through Two‐Stage Analogical Mapping

Solving Geometric Analogy Problems Through Two‐Stage Analogical Mapping

On the visual analytic intelligence of neural networks

A Review of Emerging Research Directions in Abstract Visual Reasoning

Contact Info

Product

Resources

About