Zobrazeno 1 - 10
of 113
pro vyhledávání: '"Rajan Kanaka"'
Task-trained recurrent neural networks (RNNs) are versatile models of dynamical processes widely used in machine learning and neuroscience. While RNNs are easily trained to perform a wide range of tasks, the nature and extent of the degeneracy in the
Externí odkaz:
http://arxiv.org/abs/2410.03972
The recent embrace of machine learning (ML) in the development of autonomous weapons systems (AWS) creates serious risks to geopolitical stability and the free exchange of ideas in AI research. This topic has received comparatively little attention o
Externí odkaz:
http://arxiv.org/abs/2405.01859
Autor:
Haspel, Gal, Baker, Ben, Beets, Isabel, Boyden, Edward S, Brown, Jeffrey, Church, George, Cohen, Netta, Colon-Ramos, Daniel, Dyer, Eva, Fang-Yen, Christopher, Flavell, Steven, Goodman, Miriam B, Hart, Anne C, Izquierdo, Eduardo J, Kagias, Konstantinos, Lockery, Shawn, Lu, Yangning, Marblestone, Adam, Matelsky, Jordan, Mensh, Brett, Pereira, Talmo D, Pfister, Hanspeter, Rajan, Kanaka, Rotstein, Horacio G, Scholz, Monika, Shaevitz, Joshua W., Shlizerman, Eli, Simeon, Quilee, Skuhersky, Michael A, Tiruvadi, Vineet, Venkatachalam, Vivek, Wei, Donglai, Wester, Brock, Yang, Guangyu Robert, Yemini, Eviatar, Zimmer, Manuel, Kording, Konrad P
Just like electrical engineers understand how microprocessors execute programs in terms of how transistor currents are affected by their inputs, neuroscientists want to understand behavior production in terms of how neuronal outputs are affected by t
Externí odkaz:
http://arxiv.org/abs/2308.06578
Publikováno v:
BMC Neuroscience, Vol 11, Iss Suppl 1, p O17 (2010)
Externí odkaz:
https://doaj.org/article/ed982c53c5b948b78debbd09a3cb5c0b
Biological agents do not have infinite resources to learn new things. For this reason, a central aspect of human learning is the ability to recycle previously acquired knowledge in a way that allows for faster, less resource-intensive acquisition of
Externí odkaz:
http://arxiv.org/abs/2105.14108
The deep neural nets of modern artificial intelligence (AI) have not achieved defining features of biological intelligence, including abstraction, causal learning, and energy-efficiency. While scaling to larger models has delivered performance improv
Externí odkaz:
http://arxiv.org/abs/2105.07284
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Young, Megan E., Spencer-Salmon, Camille, Mosher, Clayton, Tamang, Sarita, Rajan, Kanaka, Rudebeck, Peter H.
Publikováno v:
In Neuron 15 November 2023 111(22):3668-3682
Autor:
Akitake, Bradley, Douglas, Hannah M., LaFosse, Paul K., Beiran, Manuel, Deveau, Ciana E., O’Rawe, Jonathan, Li, Anna J., Ryan, Lauren N., Duffy, Samuel P., Zhou, Zhishang, Deng, Yanting, Rajan, Kanaka, Histed, Mark H.
Publikováno v:
In Current Biology 5 June 2023 33(11):2163-2174
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.