Author

Uri Cohen

Hebrew University of JerusalemORCID 0000-0001-8161-0430Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Neuroscience· 2

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 1 Research Focus:dimensionality reduction· 1 Assay:electronic health records· 1 Organism:mouse· 1 Approach:statistical model· 1

Frequent Co-Authors

Haim SompolinskyiD· 2 shared Andreas Savas ToliasiD· 1 shared Daniel D. LeeiD· 1 shared Edgar Y. WalkeriD· 1 shared Emmanouil FroudarakisiD· 1 shared Jacob ReimeriD· 1 shared Maria DiamantakiiD· 1 shared Philipp BerensiD· 1 shared

Activity by Year

2020-2020 · peak 2/yr

Co-Author Collaboration Network

10 top collaborators · 31 mutual co-author links

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 papersNeuroscience

Haim SompolinskyORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

NeurosciencebioRxivPreprintAug 20, 2020

Object manifold geometry across the mouse cortical visual hierarchy

Emmanouil Froudarakis, Uri Cohen, Maria Diamantaki…·Andreas Savas Tolias

Recordings of thousands of mouse visual cortex neurons reveal that lateral areas LM, LI, and AL carry higher linearly decodable object information associated with reduced object manifold dimension and radius.

44 citations

mouseelectronic health records

𝕏 PostBluesky

NeuroscienceNature CommunicationsPeer-reviewedFeb 6, 2020

Separability and Geometry of Object Manifolds in Deep Neural Networks

Uri Cohen, SueYeon Chung, Daniel D. Lee, Haim Sompolinsky

This study examines how classification capacity in deep neural networks improves with hierarchy, showing that changes in object manifold geometry underlie this improvement.

188 citationstop 1%

deep learning

𝕏 PostBluesky