Author

Eric Elmoznino

Johns Hopkins UniversityORCID 0000-0002-4608-9712Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Animal Behavior & Cognition· 1 Neuroscience· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 2 Organism:human· 2 Organism:mouse· 2 Approach:statistical model· 2 Research Focus:benchmarking· 1 Research Focus:cell type annotation· 1 Research Focus:clustering· 1 Research Focus:dimensionality reduction· 1

Frequent Co-Authors

Michael BonneriD· 2 shared Atlas KazemianiD· 1 shared

Activity by Year

2024-2025 · peak 1/yr

Co-Author Collaboration Network

2 top collaborators · 1 mutual co-author link

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

2 shared papersAnimal Behavior & Cognition

Michael BonnerORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

Animal Behavior & CognitionNature Machine IntelligencePeer-reviewedNov 13, 2025

Convolutional architectures are cortex-aligned de novo

Atlas Kazemian, Eric Elmoznino, Michael Bonner

The paper shows that convolutional neural networks with minimal training can produce cortex-aligned visual representations through specific dimensionality manipulations, suggesting architectural constraints are key.

13 citationstop 3%

humanmouse

𝕏 PostBluesky

NeurosciencePLoS Computational BiologyPeer-reviewedJan 10, 2024

High-performing neural network models of visual cortex benefit from high latent dimensionality

Eric Elmoznino, Michael Bonner

This study shows that high-dimensional latent spaces improve generalization in DNN models of visual cortex when predicting cortical responses to new stimuli.

49 citationstop 1%

humanmouse

𝕏 PostBluesky