Convolutional neural networks as a model of the visual system: Past, present, and future

GW Lindsay - Journal of cognitive neuroscience, 2021 - direct.mit.edu
Convolutional neural networks (CNNs) were inspired by early findings in the study of
biological vision. They have since become successful tools in computer vision and state-of …

Artificial neural networks for neuroscientists: a primer

GR Yang, XJ Wang - Neuron, 2020 - cell.com
Artificial neural networks (ANNs) are essential tools in machine learning that have drawn
increasing attention in neuroscience. Besides offering powerful techniques for data analysis …

Getting aligned on representational alignment

I Sucholutsky, L Muttenthaler, A Weller, A Peng… - arXiv preprint arXiv …, 2023 - arxiv.org
Biological and artificial information processing systems form representations that they can
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …

The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks

F Zenke, TP Vogels - Neural computation, 2021 - direct.mit.edu
Brains process information in spiking neural networks. Their intricate connections shape the
diverse functions these networks perform. Yet how network connectivity relates to function is …

Superspike: Supervised learning in multilayer spiking neural networks

F Zenke, S Ganguli - Neural computation, 2018 - direct.mit.edu
A vast majority of computation in the brain is performed by spiking neural networks. Despite
the ubiquity of such spiking, we currently lack an understanding of how biological spiking …

Understanding the retinal basis of vision across species

T Baden, T Euler, P Berens - Nature Reviews Neuroscience, 2020 - nature.com
The vertebrate retina first evolved some 500 million years ago in ancestral marine
chordates. Since then, the eyes of different species have been tuned to best support their …

Towards the neural population doctrine

S Saxena, JP Cunningham - Current opinion in neurobiology, 2019 - Elsevier
Highlights•New generations of recording and computing technologies have enabled
neuroscience at the level of the neural population.•Landmark scientific findings suggest the …

Exponential expressivity in deep neural networks through transient chaos

B Poole, S Lahiri, M Raghu… - Advances in neural …, 2016 - proceedings.neurips.cc
We combine Riemannian geometry with the mean field theory of high dimensional chaos to
study the nature of signal propagation in deep neural networks with random weights. Our …

Adversarial examples that fool both computer vision and time-limited humans

G Elsayed, S Shankar, B Cheung… - Advances in neural …, 2018 - proceedings.neurips.cc
Abstract Machine learning models are vulnerable to adversarial examples: small changes to
images can cause computer vision models to make mistakes such as identifying a school …

Deep convolutional models improve predictions of macaque V1 responses to natural images

SA Cadena, GH Denfield, EY Walker… - PLoS computational …, 2019 - journals.plos.org
Despite great efforts over several decades, our best models of primary visual cortex (V1) still
predict spiking activity quite poorly when probed with natural stimuli, highlighting our limited …