A Rational Model of Dimension-reduced Human Categorization

2023-05-22 · Yifan Hong, Chen Wang

Humans can categorize with only a few samples despite the numerous features. To mimic this ability, we propose a novel dimension-reduced category representation using a mixture of probabilistic principal component analyzers (mPPCA). Tests on the ${\tt CIFAR-10H}$ dataset demonstrate that mPPCA with only a single principal component for each category effectively predicts human categorization of natural images. We further impose a hierarchical prior on mPPCA to account for new category generalization. mPPCA captures human behavior in our experiments on images with simple size-color combinations. We also provide sufficient and necessary conditions when reducing dimensions in categorization is rational.

📄 PDF Abstract BibTeX arXiv:2305.14383

Code (0)

등록된 구현이 없습니다.

Tasks

Few-Shot LearningmodelZero-Shot Learning

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Kaiming Initialization 설명 없음

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

A Rational Account of Categorization Based on Information Theory

2026-02-07 · Christopher J. MacLellan, Karthik Singaravadivelan, Xin Lian, Zekun Wang 외 arxiv

We present a new theory of categorization based on an information-theoretic rational analysis. To evaluate this theory, we investigate how well it can account for key findings from classic categorization experiments cond…

Hierarchical Learning of Dimensional Biases in Human Categorization

2009-12-01 · NeurIPS 2009 12 · Adam Sanborn, Nick Chater, Katherine A. Heller

Existing models of categorization typically represent to-be-classified items as points in a multidimensional space. While from a mathematical point of view, an infinite number of basis sets can be used to represent point…

Capturing human categorization of natural images at scale by combining deep networks and cognitive models

2019-04-26 · Ruairidh M. Battleday, Joshua C. Peterson, Thomas L. Griffiths

Human categorization is one of the most important and successful targets of cognitive modeling in psychology, yet decades of development and assessment of competing models have been contingent on small sets of simple, ar…

Generalized Categorization Axioms

2015-03-31 · Jian Yu

Categorization axioms have been proposed to axiomatizing clustering results, which offers a hint of bridging the difference between human recognition system and machine learning through an intuitive observation: an objec…

BIG-bench Machine Learning Clustering Density Estimation Dimensionality Reduction

Order from Chaos: Comparative Study of Ten Leading LLMs on Unstructured Data Categorization

2025-10-14 · Ariel Kamen arxiv

This study presents a comparative evaluation of ten state-of-the-art large language models (LLMs) applied to unstructured text categorization using the Interactive Advertising Bureau (IAB) 2.2 hierarchical taxonomy. The …