Search Results for author: Martin Schrimpf

Found 15 papers, 9 papers with code

Instruction-tuning Aligns LLMs to the Human Brain

no code implementations1 Dec 2023 Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi, Martin Schrimpf, Antoine Bosselut

To identify the factors underlying LLM-brain alignment, we compute correlations between the brain alignment of LLMs and various model properties, such as model size, various problem-solving abilities, and performance on tasks requiring world knowledge spanning various domains.

Natural Language Queries World Knowledge

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

no code implementations23 Aug 2022 Anna A. Ivanova, Martin Schrimpf, Stefano Anzellotti, Noga Zaslavsky, Evelina Fedorenko, Leyla Isik

Moreover, we argue that, instead of categorically treating the mapping models as linear or nonlinear, we should instead aim to estimate the complexity of these models.


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

1 code implementation Proceedings of the National Academy of Sciences 2021 Martin Schrimpf, Idan Blank, Greta Tuckute, Carina Kauf, Eghbal Hosseini, Nancy Kanwisher, Joshua Tenenbaum, Evelina Fedorenko

The neuroscience of perception has recently been revolutionized with an integrative modeling approach in which computation, brain function, and behavior are linked across many datasets and many computational models.

Language Modelling Probing Language Models +1

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

1 code implementation ICLR 2022 Franziska Geiger, Martin Schrimpf, Tiago Marques, James J. DiCarlo

Relative to the current leading model of the adult ventral stream, we here demonstrate that the total number of supervised weight updates can be substantially reduced using three complementary strategies: First, we find that only 2% of supervised updates (epochs and images) are needed to achieve ~80% of the match to adult ventral stream.

Developmental Learning Object Recognition

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

1 code implementation NeurIPS 2020 Joel Dapello, Tiago Marques, Martin Schrimpf, Franziska Geiger, David Cox, James J. DiCarlo

Current state-of-the-art object recognition models are largely based on convolutional neural network (CNN) architectures, which are loosely inspired by the primate visual system.

Object Recognition

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

1 code implementation2 Jan 2020 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

We therefore developed Brain-Score – a composite of multiple neural and behavioral benchmarks that score any ANN on how similar it is to the brain’s mechanisms for core object recognition – and we deployed it to evaluate a wide range of state-of-the-art deep ANNs.

Object Recognition

Frivolous Units: Wider Networks Are Not Really That Wide

1 code implementation10 Dec 2019 Stephen Casper, Xavier Boix, Vanessa D'Amario, Ling Guo, Martin Schrimpf, Kasper Vinken, Gabriel Kreiman

We identify two distinct types of "frivolous" units that proliferate when the network's width is increased: prunable units which can be dropped out of the network without significant change to the output and redundant units whose activities can be expressed as a linear combination of others.

Aligning Artificial Neural Networks to the Brain yields Shallow Recurrent Architectures

no code implementations ICLR 2019 Jonas Kubilius, Martin Schrimpf, Ha Hong, Najib J. Majaj, Rishi Rajalingham, Elias B. Issa, Kohitij Kar, Pouya Bashivan, Jonathan Prescott-Roy, Kailyn Schmidt, Aran Nayebi, Daniel Bear, Daniel L. K. Yamins, James J. DiCarlo

Deep artificial neural networks with spatially repeated processing (a. k. a., deep convolutional ANNs) have been established as the best class of candidate models of visual processing in the primate ventral visual processing stream.

Anatomy Object Categorization

Continual Learning with Self-Organizing Maps

no code implementations19 Apr 2019 Pouya Bashivan, Martin Schrimpf, Robert Ajemian, Irina Rish, Matthew Riemer, Yuhai Tu

Most previous approaches to this problem rely on memory replay buffers which store samples from previously learned tasks, and use them to regularize the learning on new ones.

Continual Learning

Recurrent computations for visual pattern completion

1 code implementation7 Jun 2017 Hanlin Tang, Martin Schrimpf, Bill Lotter, Charlotte Moerman, Ana Paredes, Josue Ortega Caro, Walter Hardesty, David Cox, Gabriel Kreiman

First, subjects robustly recognized objects even when rendered <15% visible, but recognition was largely impaired when processing was interrupted by backward masking.

Image Classification

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

1 code implementation23 Mar 2017 Nicholas Cheney, Martin Schrimpf, Gabriel Kreiman

We show that convolutional networks are surprisingly robust to a number of internal perturbations in the higher convolutional layers but the bottom convolutional layers are much more fragile.

Should I use TensorFlow

no code implementations27 Nov 2016 Martin Schrimpf

I also contrast TensorFlow to other popular frameworks with respect to modeling capability, deployment and performance and give a brief description of the current adaption of the framework.

BIG-bench Machine Learning General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.