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 …

Are deep neural networks adequate behavioral models of human visual perception?

FA Wichmann, R Geirhos - Annual Review of Vision Science, 2023 - annualreviews.org
Deep neural networks (DNNs) are machine learning algorithms that have revolutionized
computer vision due to their remarkable successes in tasks like object classification and …

Partial success in closing the gap between human and machine vision

R Geirhos, K Narayanappa, B Mitzkus… - Advances in …, 2021 - proceedings.neurips.cc
A few years ago, the first CNN surpassed human performance on ImageNet. However, it
soon became clear that machines lack robustness on more challenging test cases, a major …

Unsupervised neural network models of the ventral visual stream

C Zhuang, S Yan, A Nayebi… - Proceedings of the …, 2021 - National Acad Sciences
Deep neural networks currently provide the best quantitative models of the response
patterns of neurons throughout the primate ventral visual stream. However, such networks …

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 …

The neural architecture of language

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

[PDF][PDF] Integrative benchmarking to advance neurally mechanistic models of human intelligence

M Schrimpf, J Kubilius, MJ Lee, NAR Murty, R Ajemian… - Neuron, 2020 - cell.com
A potentially organizing goal of the brain and cognitive sciences is to accurately explain
domains of human intelligence as executable, neurally mechanistic models. Years of …

Deep problems with neural network models of human vision

JS Bowers, G Malhotra, M Dujmović… - Behavioral and Brain …, 2023 - cambridge.org
Deep neural networks (DNNs) have had extraordinary successes in classifying
photographic images of objects and are often described as the best models of biological …

Harmonizing the object recognition strategies of deep neural networks with humans

T Fel, IF Rodriguez Rodriguez… - Advances in neural …, 2022 - proceedings.neurips.cc
The many successes of deep neural networks (DNNs) over the past decade have largely
been driven by computational scale rather than insights from biological intelligence. Here …

Limits to visual representational correspondence between convolutional neural networks and the human brain

Y Xu, M Vaziri-Pashkam - Nature communications, 2021 - nature.com
Convolutional neural networks (CNNs) are increasingly used to model human vision due to
their high object categorization capabilities and general correspondence with human brain …