Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Capturing Human Category Representations by Sampling in Deep Feature Spaces
Nov 03, 2017 (modified: Nov 03, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Understanding how people represent categories is a core problem in cognitive science, with the flexibility of human learning remaining a gold standard to which modern artificial intelligence and machine learning aspires. Decades of psychological research have yielded a variety of formal theories of categories, yet validating these theories with naturalistic stimuli remains a challenge. The problem is that human category representations cannot be directly observed and running informative experiments with naturalistic stimuli such as images requires having a reasonable representation of these images. Deep neural networks have recently been successful in a range of computer vision tasks and provide a way to represent the features of images. In this paper, we outline a method for estimating the structure of human categories that draws on ideas from both cognitive science and machine learning, blending human-based algorithms with state-of-the-art deep representation learners. We provide qualitative and quantitative results as a proof of concept for the feasibility of the method. Samples drawn from human distributions rival the quality of current state-of-the-art generative models and outperform alternative methods for estimating the structure of human categories.
TL;DR:using deep neural networks and clever algorithms to capture human mental visual concepts
Keywords:category representations, psychology, cognitive science, deep neural networks
Enter your feedback below and we'll get back to you as soon as possible.