Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Eric Hunsberger"'
Publikováno v:
IEEE Access, Vol 5, Pp 11645-11657 (2017)
The most accurate stereo disparity algorithms take dozens or hundreds of seconds to process a single frame. This timescale is impractical for many applications. However, high accuracy is often not needed throughout the scene. Here, we investigate a
Externí odkaz:
https://doaj.org/article/c82ee0661edd4d0592ad38ccfb5490a2
Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::455aab504bed085f7d2322434e2cb19f
http://arxiv.org/abs/1812.01739
http://arxiv.org/abs/1812.01739
Publikováno v:
Neural computation. 26(8)
Noise and heterogeneity are both known to benefit neural coding. Stochastic resonance describes how noise, in the form of random fluctuations in a neuron's membrane voltage, can improve neural representations of an input signal. Neuronal heterogeneit
Autor:
James Bergstra, Xuan Choo, Trevor Bekolay, Aaron R. Voelker, Daniel Rasmussen, Terrence C. Stewart, Chris Eliasmith, Travis DeWolf, Eric Hunsberger
Publikováno v:
Frontiers in Neuroinformatics, Vol 7 (2014)
Frontiers in Neuroinformatics
Frontiers in Neuroinformatics
Neuroscience currently lacks a comprehensive theory of how cognitive processes can be implemented in a biological substrate. The Neural Engineering Framework (NEF) proposes one such theory, but has not yet gathered significant empirical support, part