Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Lane, McIntosh"'
From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction
Autor:
Hidenori, Tanaka, Aran, Nayebi, Niru, Maheswaranathan, Lane, McIntosh, Stephen A, Baccus, Surya, Ganguli
Publikováno v:
Adv Neural Inf Process Syst
Recently, deep feedforward neural networks have achieved considerable success in modeling biological sensory processing, in terms of reproducing the input-output map of sensory neurons. However, such models raise profound questions about the very nat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::83a70b04e17b50f16350f27228827feb
https://pubmed.ncbi.nlm.nih.gov/35283616
https://pubmed.ncbi.nlm.nih.gov/35283616
Autor:
Xuehao Ding, Dongsoo Lee, Satchel Grant, Heike Stein, Lane McIntosh, Niru Maheswaranathan, Stephen Baccus
The visual system processes stimuli over a wide range of spatiotemporal scales, with individual neurons receiving input from tens of thousands of neurons whose dynamics range from milliseconds to tens of seconds. This poses a challenge to create mode
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8d290786c8d01199e9efd3051295698
https://doi.org/10.1101/2021.12.18.473320
https://doi.org/10.1101/2021.12.18.473320
Autor:
Jianbin Wang, Lane McIntosh, Aran Nayebi, Grant S, Stephen A. Baccus, Surya Ganguli, David B. Kastner, Niru Maheswaranathan, Tanaka H, Brezovec L, Joshua B. Melander
Understanding how the visual system encodes natural scenes is a fundamental goal of sensory neuroscience. We show here that a three-layer network model predicts the retinal response to natural scenes with an accuracy nearing the fundamental limits of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f7fc72e7b880ef30fc83eecb597a69f
https://doi.org/10.1101/340943
https://doi.org/10.1101/340943
Publikováno v:
CVPR Workshops
State-of-the-art systems for semantic image segmentation use feed-forward pipelines with fixed computational costs. Building an image segmentation system that works across a range of computational budgets is challenging and time-intensive as new arch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9de8b413ee8a58f41983d821c3c48cc