Zobrazeno 1 - 10
of 984
pro vyhledávání: '"Jose C Principe"'
Autor:
Salvador eDura-Bernal, Kan eLi, Samuel A Neymotin, Joseph T Francis, Jose C Principe, William W Lytton
Publikováno v:
Frontiers in Neuroscience, Vol 10 (2016)
Neural stimulation can be used as a tool to elicit natural sensations or behaviors by modulating neural activity. This can be potentially used to mitigate the damage of brain lesions or neural disorders. However, in order to obtain the optimal stimul
Externí odkaz:
https://doaj.org/article/f6b451c41af34251bb2da59962576344
Autor:
In Jun Park, Andrew M Hein, Yuriy V Bobkov, Matthew A Reidenbach, Barry W Ache, Jose C Principe
Publikováno v:
PLoS Computational Biology, Vol 12, Iss 1, p e1004682 (2016)
Accurately encoding time is one of the fundamental challenges faced by the nervous system in mediating behavior. We recently reported that some animals have a specialized population of rhythmically active neurons in their olfactory organs with the po
Externí odkaz:
https://doaj.org/article/4515483e64f946b79e12bf20b1333227
Leading researchers in signal processing and neural computation present work aimed at promoting the interaction and cross-fertilization between the two fields. Signal processing and neural computation have separately and significantly influenced many
Autor:
Shiyu Duan, Jose C. Principe
Publikováno v:
IEEE Computational Intelligence Magazine. 17:39-51
This tutorial paper surveys provably optimal alternatives to end-to-end backpropagation (E2EBP) -- the de facto standard for training deep architectures. Modular training refers to strictly local training without both the forward and the backward pas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::97ab320ef9110d5a9859f3bf512b6c94
https://doi.org/10.1109/mci.2022.3199624
https://doi.org/10.1109/mci.2022.3199624
Publikováno v:
Neural Networks. 150:274-292
Inspired by the human vision system and learning, we propose a novel cognitive architecture that understands the content of raw videos in terms of objects without using labels. The architecture achieves four objectives: (1) Decomposing raw frames in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65ff87426ec59fc3e3a1ae852d1db6c1
https://doi.org/10.1016/j.neunet.2022.02.029
https://doi.org/10.1016/j.neunet.2022.02.029
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:1441-1451
By redefining the conventional notions of layers, we present an alternative view on finitely wide, fully trainable deep neural networks as stacked linear models in feature spaces, leading to a kernel machine interpretation. Based on this construction
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e68acda4541f33dd001606ec019ebdef
https://doi.org/10.1109/tnnls.2020.3042346
https://doi.org/10.1109/tnnls.2020.3042346
Publikováno v:
Journal of Marine Science and Engineering, Vol 9, Iss 2, p 157 (2021)
Deep neural networks provide remarkable performances on supervised learning tasks with extensive collections of labeled data. However, creating such large well-annotated data sets requires a considerable amount of resources, time and effort, especial
Externí odkaz:
https://doaj.org/article/e2e093ce75304cffb201036ea0d2c50f
Distinct dynamics in different cortical layers are apparent in both neuronal and local field potential (LFP) patterns. Yet, the associations between spiking activity and LFPs in the context of laminar processing within and across cortices have only b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a6abbf4c54454a1695c42ab095812440
https://doi.org/10.1101/2023.01.17.524451
https://doi.org/10.1101/2023.01.17.524451
Autor:
Carlos A. Loza, Jose C. Principe
Publikováno v:
Handbook of Neuroengineering ISBN: 9789811655395
Handbook of Neuroengineering ISBN: 9789811528484
Handbook of Neuroengineering
Handbook of Neuroengineering ISBN: 9789811528484
Handbook of Neuroengineering
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b16f676a65387e65469e6ba97a339d24
https://doi.org/10.1007/978-981-16-5540-1_65
https://doi.org/10.1007/978-981-16-5540-1_65
Publikováno v:
Neural Networks. 141:145-159
Deep learning architectures are an extremely powerful tool for recognizing and classifying images. However, they require supervised learning and normally work on vectors of the size of image pixels and produce the best results when trained on million
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::622d9e71740825af20d3483e083e42ef
https://doi.org/10.1016/j.neunet.2021.03.003
https://doi.org/10.1016/j.neunet.2021.03.003