Representations and generalization in artificial and brain neural networks

Q Li, B Sorscher, H Sompolinsky - Proceedings of the National Academy of …, 2024 - pnas.org
Humans and animals excel at generalizing from limited data, a capability yet to be fully
replicated in artificial intelligence. This perspective investigates generalization in biological …

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

M Schrimpf, IA Blank, G Tuckute… - Proceedings of the …, 2021 - National Acad Sciences
The neuroscience of perception has recently been revolutionized with an integrative
modeling approach in which computation, brain function, and behavior are linked across …

An ecologically motivated image dataset for deep learning yields better models of human vision

J Mehrer, CJ Spoerer, EC Jones… - Proceedings of the …, 2021 - National Acad Sciences
Deep neural networks provide the current best models of visual information processing in
the primate brain. Drawing on work from computer vision, the most commonly used networks …

Building transformers from neurons and astrocytes

L Kozachkov, KV Kastanenka… - Proceedings of the …, 2023 - National Acad Sciences
Glial cells account for between 50% and 90% of all human brain cells, and serve a variety of
important developmental, structural, and metabolic functions. Recent experimental efforts …

Texture-like representation of objects in human visual cortex

AV Jagadeesh, JL Gardner - Proceedings of the National …, 2022 - National Acad Sciences
The human visual ability to recognize objects and scenes is widely thought to rely on
representations in category-selective regions of the visual cortex. These representations …

Neural representational geometry underlies few-shot concept learning

B Sorscher, S Ganguli… - Proceedings of the …, 2022 - National Acad Sciences
Understanding the neural basis of the remarkable human cognitive capacity to learn novel
concepts from just one or a few sensory experiences constitutes a fundamental problem. We …

High-performing neural network models of visual cortex benefit from high latent dimensionality

E Elmoznino, MF Bonner - PLOS Computational Biology, 2024 - journals.plos.org
Geometric descriptions of deep neural networks (DNNs) have the potential to uncover core
representational principles of computational models in neuroscience. Here we examined the …

Learning efficient coding of natural images with maximum manifold capacity representations

T Yerxa, Y Kuang, E Simoncelli… - Advances in Neural …, 2023 - proceedings.neurips.cc
The efficient coding hypothesis proposes that the response properties of sensory systems
are adapted to the statistics of their inputs such that they capture maximal information about …

Emergence of a compositional neural code for written words: Recycling of a convolutional neural network for reading

T Hannagan, A Agrawal, L Cohen… - Proceedings of the …, 2021 - National Acad Sciences
The visual word form area (VWFA) is a region of human inferotemporal cortex that emerges
at a fixed location in the occipitotemporal cortex during reading acquisition and …

Rich and lazy learning of task representations in brains and neural networks

T Flesch, K Juechems, T Dumbalska, A Saxe… - BioRxiv, 2021 - biorxiv.org
How do neural populations code for multiple, potentially conflicting tasks? Here, we used
computational simulations involving neural networks to define “lazy” and “rich” coding …