Probabilistic Analogical Mapping with Semantic Relation Networks
- URL: http://arxiv.org/abs/2103.16704v1
- Date: Tue, 30 Mar 2021 22:14:13 GMT
- Title: Probabilistic Analogical Mapping with Semantic Relation Networks
- Authors: Hongjing Lu, Nicholas Ichien, Keith J. Holyoak
- Abstract summary: We present a new computational model of analogical mapping, based on semantic relation networks.
We show that the model accounts for a broad range of phenomena involving analogical mapping by both adults and children.
- Score: 2.084078990567849
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: The human ability to flexibly reason with cross-domain analogies depends on
mechanisms for identifying relations between concepts and for mapping concepts
and their relations across analogs. We present a new computational model of
analogical mapping, based on semantic relation networks constructed from
distributed representations of individual concepts and of relations between
concepts. Through comparisons with human performance in a new analogy
experiment with 1,329 participants, as well as in four classic studies, we
demonstrate that the model accounts for a broad range of phenomena involving
analogical mapping by both adults and children. The key insight is that rich
semantic representations of individual concepts and relations, coupled with a
generic prior favoring isomorphic mappings, yield human-like analogical
mapping.
Related papers
- Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks [3.001674556825579]
Understanding how neural networks align with human cognitive processes is a crucial step toward developing more interpretable and reliable AI systems.
We identify a correlation between these two dimensions that reflect the similarity relations humans in cognitive tasks.
This presents a first step toward understanding the relationship convexity between human-machine alignment.
arXiv Detail & Related papers (2024-09-10T09:32:16Z) - Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models.
We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model.
We substantiate our theoretical claims with synthetic data experiments.
arXiv Detail & Related papers (2024-06-01T18:01:03Z) - A Recursive Bateson-Inspired Model for the Generation of Semantic Formal
Concepts from Spatial Sensory Data [77.34726150561087]
This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data.
The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept.
The model is able to produce fairly rich yet human-readable conceptual representations without training.
arXiv Detail & Related papers (2023-07-16T15:59:13Z) - Counting Like Human: Anthropoid Crowd Counting on Modeling the
Similarity of Objects [92.80955339180119]
mainstream crowd counting methods regress density map and integrate it to obtain counting results.
Inspired by this, we propose a rational and anthropoid crowd counting framework.
arXiv Detail & Related papers (2022-12-02T07:00:53Z) - Similarity of Neural Architectures using Adversarial Attack Transferability [47.66096554602005]
We design a quantitative and scalable similarity measure between neural architectures.
We conduct a large-scale analysis on 69 state-of-the-art ImageNet classifiers.
Our results provide insights into why developing diverse neural architectures with distinct components is necessary.
arXiv Detail & Related papers (2022-10-20T16:56:47Z) - Evaluation of taxonomic and neural embedding methods for calculating
semantic similarity [0.0]
We study the mechanisms between taxonomic and distributional similarity measures.
We find that taxonomic similarity measures can depend on the shortest path length as a prime factor to predict semantic similarity.
The synergy of retrofitting neural embeddings with concept relations in similarity prediction may indicate a new trend to leverage knowledge bases on transfer learning.
arXiv Detail & Related papers (2022-09-30T02:54:21Z) - Image Synthesis via Semantic Composition [74.68191130898805]
We present a novel approach to synthesize realistic images based on their semantic layouts.
It hypothesizes that for objects with similar appearance, they share similar representation.
Our method establishes dependencies between regions according to their appearance correlation, yielding both spatially variant and associated representations.
arXiv Detail & Related papers (2021-09-15T02:26:07Z) - Visual stream connectivity predicts assessments of image quality [0.0]
We derive a novel formalization of the psychophysics of similarity, showing the differential geometry that provides accurate and explanatory accounts of perceptual similarity judgments.
Predictions are further improved via simple regression on human behavioral reports, which in turn are used to construct more elaborate hypothesized neural connectivity patterns.
arXiv Detail & Related papers (2020-08-16T15:38:17Z) - Analogy as Nonparametric Bayesian Inference over Relational Systems [10.736626320566705]
We propose a Bayesian model that generalizes relational knowledge to novel environments by analogically weighting predictions from previously encountered relational structures.
We show that this learner outperforms a naive, theory-based learner on relational data derived from random- and Wikipedia-based systems when experience with the environment is small.
arXiv Detail & Related papers (2020-06-07T14:07:46Z) - Neural Analogical Matching [8.716086137563243]
The importance of analogy to humans has made it an active area of research in the broader field of artificial intelligence.
We introduce the Analogical Matching Network, a neural architecture that learns to produce analogies between structured, symbolic representations.
arXiv Detail & Related papers (2020-04-07T17:50:52Z) - Hierarchical Human Parsing with Typed Part-Relation Reasoning [179.64978033077222]
How to model human structures is the central theme in this task.
We seek to simultaneously exploit the representational capacity of deep graph networks and the hierarchical human structures.
arXiv Detail & Related papers (2020-03-10T16:45:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.