246 citations · 552 across the 25 of their papers we have counts for
7 papers · 1 filter
Reward Valuation in Large Language Models: Causal Induction of Anhedonia
Melika Honarmand, Samin Mahdipour Aghabagher, Martin Schrimpf
Recent frontier models mimic complex aspects of human cognition. Here we ask whether this alignment extends into reward valuation, which we assess in a mechanistic framework. Speci…
MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding
Abdulkadir Gokce, Badr AlKhamissi, Martin Schrimpf
Recent progress in task-optimized neural networks has established encoding models as a powerful tool for predicting brain responses to naturalistic stimuli, yet most existing appro…
Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization
Badr AlKhamissi, C. Nicolò De Sabbata, Greta Tuckute +3
Human cognitive behavior arises from the interaction of specialized brain networks dedicated to distinct functions, such as language, logic, and social reasoning. Inspired by this…
Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
Abdulkadir Gokce, Martin Schrimpf
When trained on large-scale object classification datasets, certain artificial neural network models begin to approximate core object recognition behaviors and neural response patt…
Frivolous Units: Wider Networks Are Not Really That Wide
Stephen Casper, Xavier Boix, Vanessa D'Amario +4
A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests…
On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
Nicholas Cheney, Martin Schrimpf, Gabriel Kreiman
Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images…
Should I use TensorFlow
Martin Schrimpf
Google's Machine Learning framework TensorFlow was open-sourced in November 2015 [1] and has since built a growing community around it. TensorFlow is supposed to be flexible for re…