Martin Schrimpf

发表

Multi-scale hierarchical neural network models that bridge from single neurons in the primate primary visual cortex to object recognition behavior

Martin Schrimpf, James J. DiCarlo, Tiago Marques, 2021, bioRxiv.

The neural architecture of language: Integrative reverse-engineering converges on a model for predictive processing

Nancy Kanwisher, Carina Kauf, Martin Schrimpf, 2020 .

Integrative Benchmarking to Advance Neurally Mechanistic Models of Human Intelligence

Jonas Kubilius, Martin Schrimpf, James J. DiCarlo, 2020, Neuron.

Unsupervised neural network models of the ventral visual stream

Michael C. Frank, Martin Schrimpf, Chengxu Zhuang, 2020, Proceedings of the National Academy of Sciences.

Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness

David D. Cox, J. DiCarlo, D. Cox, 2022, bioRxiv.

Beyond linear regression: mapping models in cognitive neuroscience should align with research goals

Anna A. Ivanova, Leyla Isik, Evelina Fedorenko, 2021, bioRxiv.

Artificial neural network language models align neurally and behaviorally with humans even after a developmentally realistic amount of training

Samuel R. Bowman, Eghbal A. Hosseini, Evelina Fedorenko, 2022, bioRxiv.

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

Martin Schrimpf, James J. DiCarlo, Franziska Geiger, 2020, bioRxiv.

ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation

Josh H. McDermott, Daniel L. K. Yamins, Julian De Freitas, 2020, NeurIPS Datasets and Benchmarks.

On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations pdf

Gabriel Kreiman, Martin Schrimpf, Nicholas Cheney, 2017, ArXiv.

Recurrent computations for visual pattern completion

David Cox, Gabriel Kreiman, Hanlin Tang, 2017, Proceedings of the National Academy of Sciences.

The neural architecture of language: Integrative modeling converges on predictive processing

Eghbal A. Hosseini, J. Tenenbaum, N. Kanwisher, 2020, Proceedings of the National Academy of Sciences.

Artificial Neural Networks Accurately Predict Language Processing in the Brain

Nancy Kanwisher, Carina Kauf, Martin Schrimpf, 2020 .

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

Martin Schrimpf, David D. Cox, James J. DiCarlo, 2020, bioRxiv.

Integrative Benchmarking to Advance Neurally Mechanistic Models of Human Intelligence

Jonas Kubilius, Martin Schrimpf, James J. DiCarlo, 2020, Neuron.

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

Jonas Kubilius, Martin Schrimpf, Ha Hong, 2018, bioRxiv.

CORnet: Modeling the Neural Mechanisms of Core Object Recognition

Aran Nayebi, Jonas Kubilius, Martin Schrimpf, 2018, bioRxiv.

Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs

Elias B. Issa, Daniel L. K. Yamins, J. DiCarlo, 2019, NeurIPS.

The neural architecture of language: Integrative reverse-engineering converges on a model for predictive processing

Eghbal A. Hosseini, J. Tenenbaum, N. Kanwisher, 2020 .

Is it that simple? The use of linear models in cognitive neuroscience

Martin Schrimpf, Evelina Fedorenko, Leyla Isik, 2020 .

Driving and suppressing the human language network using large language models

Evelina Fedorenko, Kendrick Norris Kay, Shashank Srikant, 2023, bioRxiv.

Uhr Institute for Software & Systems Engineering Universitätsstraße 6 a D-86135 Augsburg Brain-inspired Recurrent Neural Algorithms for Advanced Object Recognition

Martin Schrimpf, Martin Schrimpf, 2016 .

Is it that simple? Linear mapping models in cognitive neuroscience

Anna A. Ivanova, Leyla Isik, Noga Zaslavsky, 2021 .

A Flexible Approach to Automated RNN Architecture Generation pdf

Richard Socher, Martin Schrimpf, James Bradbury, 2017, ICLR.

Single units in a deep neural network functionally correspond with neurons in the brain: preliminary results

Martin Schrimpf, Tomaso Poggio, Pouya Bashivan, 2018 .

Continual Learning with Self-Organizing Maps pdf

Martin Schrimpf, Pouya Bashivan, Irina Rish, 2019, ArXiv.

Removable and/or Repeated Units Emerge in Overparametrized Deep Neural Networks pdf

Vanessa D'Amario, Gabriel Kreiman, Martin Schrimpf, 2019, ArXiv.

CORnet: Modeling the Neural Mechanisms of Core Object Recognition

J. DiCarlo, Daniel Yamins, Aran Nayebi, 2018, bioRxiv.

Large-scale hyperparameter search for predicting human brain responses in the Algonauts challenge

Martin Schrimpf, Pouya Bashivan, Kamila M. Jozwik, 2019, bioRxiv.

To find better neural network models of human vision, find better neural network models of primate vision

Nancy Kanwisher, Martin Schrimpf, James J. DiCarlo, 2019, bioRxiv.

Driving and suppressing the human language network using large language models

Evelina Fedorenko, Kendrick Norris Kay, Shashank Srikant, 2023, bioRxiv.

Primate Inferotemporal Cortex Neurons Generalize Better to Novel Image Distributions Than Corresponding Deep Neural Networks Units

J. DiCarlo, Tiago Marques, Martin Schrimpf, 2023 .

Artificial Neural Network Language Models Predict Human Brain Responses to Language Even After a Developmentally Realistic Amount of Training

Samuel R. Bowman, Eghbal A. Hosseini, Evelina Fedorenko, 2023, bioRxiv.

Driving and suppressing the human language network using large language models

Evelina Fedorenko, Kendrick Norris Kay, Shashank Srikant, 2023, bioRxiv.

Frivolous Units: Wider Networks Are Not Really That Wide

Vanessa D'Amario, Gabriel Kreiman, Martin Schrimpf, 2019, AAAI.

Driving and suppressing the human language network using large language models

Evelina Fedorenko, Shashank Srikant, Martin Schrimpf, 2024, Nature human behaviour.

Do Topographic Deep ANN Models of the Primate Ventral Stream Predict the Perceptual Effects of Direct IT Cortical Interventions?

J. DiCarlo, Martin Schrimpf, Eshed Margalit, 2024, bioRxiv.