Author

Franziska Geiger

McGovern Institute for Brain Research

Listed by name: these papers carry no ORCID for this author, so different people with the same name may be mixed together.

Biology Disciplines

Click to filter author papers

Neuroscience· 3 Bioengineering· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 4 Research Focus:benchmarking· 2 Research Focus:drug response / drug discovery· 2 Organism:human· 2 Organism:non-human primate· 2 Approach:statistical model· 2 Approach:benchmark study· 1 Research Focus:database / resource· 1

Frequent Co-Authors

James J. DiCarloiD· 3 shared Martin SchrimpfiD· 3 shared Tiago MarquesiD· 2 shared Angela I. Schriek· 1 shared Arthur Lindoulsi· 1 shared Catalina IJspeert· 1 shared Christian Holberg· 1 shared Constance Ferragu· 1 shared

Activity by Year

2020-2026 · peak 3/yr

Co-Author Collaboration Network

10 top collaborators · 20 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

3 shared papersNeuroscience

James J. DiCarloORCID

Mutual co-authors in cluster

Author profile →

4 papers

Recent·Most cited

What comes after de novo? Automated lead optimization of proteins with CRADLE-1

Eli Bixby, Gino Brunner, Daniel Danciu, Richard Dela Rosa, Nicolas Deutschmann, Constance Ferragu, Franziska Geiger, Christian Holberg, Patrick Kidger, Arthur Lindoulsi, Noé Lutz, Thomas McColgan, Sebastian Millius, Harmen van Rossum, Jinel Shah, , Angela I. Schriek

CRADLE-1 automates protein lead optimization, improving speed and efficiency compared to rational design methods.

bioRxiv · Oct 16, 2026 · PreprintBioengineering

Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations

Joel Dapello, Tiago Marques, Martin Schrimpf, Franziska Geiger, David Cox, James J. DiCarlo

A fixed-weight, biologically parameterised V1 front-end gives standard image classifiers adversarial and corruption robustness at no extra training cost; its simulated neuronal noise drives most of the adversarial gain.

bioRxiv · Jun 16, 2020 · PreprintNeuroscience✦ In-depth digest

Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream

Franziska Geiger, Martin Schrimpf, Tiago Marques, James J. DiCarlo

This paper reduces the number of supervised synaptic updates needed to model the primate ventral visual stream, achieving 80% of the adult match with significantly fewer updates.

bioRxiv · Jun 8, 2020 · PreprintNeuroscience

Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like?

Martin Schrimpf, Jonas Kubilius, Ha Hong, Najib J. Majaj, Rishi Rajalingham, Elias B. Issa, Kohitij Kar, Pouya Bashivan, Jonathan Prescott-Roy, Franziska Geiger, Kailyn Schmidt, Daniel L. K. Yamins, James J. DiCarlo

Among dozens of ImageNet-trained networks scored against macaque V4/IT recordings and human behavior, DenseNet-169, CORnet-S and ResNet-101 rank highest, and brain similarity stops tracking accuracy above 70% top-1.

bioRxiv · Jan 2, 2020 · PreprintNeuroscience✦ In-depth digest