Zobrazeno 1 - 10
of 639
pro vyhledávání: '"Shim, Yong"'
In this work, we propose stochastic Binary Spiking Neural Network (sBSNN) composed of stochastic spiking neurons and binary synapses (stochastic only during training) that computes probabilistically with one-bit precision for power-efficient and memo
Externí odkaz:
http://arxiv.org/abs/2002.11163
Autor:
Shim, Yong Ju
Publikováno v:
Repositório Institucional do FGVFundação Getulio VargasFGV.
Submitted by Yong Ju Shim (morangoum@naver.com) on 2017-02-01T11:40:02Z No. of bitstreams: 1 20170201 REALLY final version for printing.pdf: 1088076 bytes, checksum: 43c4c0b955201c5a1073290a22ce2dfb (MD5)
Approved for entry into archive by Pamel
Approved for entry into archive by Pamel
Externí odkaz:
http://hdl.handle.net/10438/17819
Probabilistic inference from real-time input data is becoming increasingly popular and may be one of the potential pathways at enabling cognitive intelligence. As a matter of fact, preliminary research has revealed that stochastic functionalities als
Externí odkaz:
http://arxiv.org/abs/1707.04687
Ising spin model is considered as an efficient computing method to solve combinatorial optimization problems based on its natural tendency of convergence towards low energy state. The underlying basic functions facilitating the Ising model can be cat
Externí odkaz:
http://arxiv.org/abs/1609.05926
Non-Boolean computing based on emerging post-CMOS technologies can potentially pave the way for low-power neural computing platforms. However, existing work on such emerging neuromorphic architectures have either focused on solely mimicking the neuro
Externí odkaz:
http://arxiv.org/abs/1510.00459
We consider the fractional nonlinear Schr\"odinger equation (FNLS) with general dispersion $|\nabla|^\alpha$ and focusing energy-critical nonlinearities $-|u|^\frac{2\alpha}{d-\alpha}u$ and $-(|x|^{-2\alpha} * |u|^2) u$. By adopting Kenig-Tsutsumi \c
Externí odkaz:
http://arxiv.org/abs/1502.00100
Recent years have witnessed growing interest in the use of Artificial Neural Networks (ANNs) for vision, classification, and inference problems. An artificial neuron sums N weighted inputs and passes the result through a non-linear transfer function.
Externí odkaz:
http://arxiv.org/abs/1412.8648
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.