ArticlePatterns (New York, N.Y.)2021
Grounding deep neural network predictions of human categorization behavior in understandable functional features: The case of face identity.
Article in Patterns (New York, N.Y.), 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 18 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
18 citing papers in PubMed.
- Making models disagree to learn how brains compute.Nature reviews. Neuroscience · 2026Review
- Spatiotemporal dynamics and substates underlie emotional signalling in facial movements.Scientific reports · 2026Article
- Data-driven psychophysical methods to diversify SIAs and address bias.Journal on multimodal user interfaces · 2026Article
- Impaired face identity discrimination in individuals with cerebral visual impairment: a pilot study.Annals of translational medicine · 2025Article
- Unraveling the complexity of rat object vision requires a full convolutional network and beyond.Patterns (New York, N.Y.) · 2025Article
- Beyond Letters: Optimal Transport as a Model for Sub-Letter Orthographic Processing.Neurobiology of language (Cambridge, Mass.) · 2025Article
- The role of expansion and adaptability of face-space for individual differences in face identity processing.Royal Society open science · 2025Article
- Computational reconstruction of mental representations using human behavior.Nature communications · 2024Article
- A novel, rapid, quantitative method for face discrimination.PloS one · 2024Article
- Modeling naturalistic face processing in humans with deep convolutional neural networks.Proceedings of the National Academy of Sciences of the United States of America · 2023Article
- Advancing Naturalistic Affective Science with Deep Learning.Affective science · 2023Review
- Stimulus whitening improves the efficiency of reverse correlation.Behavior research methods · 2023Article
- Toward human-level concept learning: Pattern benchmarking for AI algorithms.Patterns (New York, N.Y.) · 2023Review
- Behavioral signatures of face perception emerge in deep neural networks optimized for face recognition.Proceedings of the National Academy of Sciences of the United States of America · 2023Article
- Face dissimilarity judgments are predicted by representational distance in morphable and image-computable models.Proceedings of the National Academy of Sciences of the United States of America · 2022Article
- Utilization of Random Forest Classifier and Artificial Neural Network for Predicting Factors Influencing the Perceived Usability of COVID-19 Contact Tracing "MorChana" in Thailand.International journal of environmental research and public health · 2022Article
- Utilization of Random Forest and Deep Learning Neural Network for Predicting Factors Affecting Perceived Usability of a COVID-19 Contact Tracing Mobile Application in Thailand "ThaiChana".International journal of environmental research and public health · 2022Article
- Understanding the evolution of a de novo molecule generator via characteristic functional group monitoring.Science and technology of advanced materials · 2022Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
7 authors.
Funding
Abstract
Deep neural networks (DNNs) can resolve real-world categorization tasks with apparent human-level performance. However, true equivalence of behavioral performance between humans and their DNN models requires that their internal mechanisms process equivalent features of the stimulus. To develop such feature equivalence, our methodology leveraged an interpretable and experimentally controlled generative model of the stimuli (realistic three-dimensional textured faces). Humans rated the similarity of randomly generated faces to four familiar identities. We predicted these similarity ratings from the activations of five DNNs trained with different optimization objectives. Using information theoretic redundancy, reverse correlation, and the testing of generalization gradients, we show that DNN predictions of human behavior improve because their shape and texture features overlap with those that subsume human behavior. Thus, we must equate the functional features that subsume the behavioral performances of the brain and its models before comparing where, when, and how these features are processed.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.