Zobrazeno 1 - 10
of 130
pro vyhledávání: '"Stosic, Dusan"'
Autor:
Toksumakov, Adilet, Ermolaev, Georgy, Tatmyshevskiy, Mikhail, Klishin, Yuri, Slavich, Aleksandr, Begichev, Ilya, Stosic, Dusan, Yakubovsky, Dmitry, Kvashnin, Dmitry, Vyshnevyy, Andrey, Arsenin, Aleksey, Volkov, Valentyn, Ghazaryan, Davit
Graphene/hBN heterostructures can be considered as one of the basic building blocks for the next-generation optoelectronics mostly owing to the record-high electron mobilities. However, currently, the studies of the intrinsic optical properties of gr
Externí odkaz:
http://arxiv.org/abs/2212.01230
This work maps deep neural networks to classical Ising spin models, allowing them to be described using statistical thermodynamics. The density of states shows that structures emerge in the weights after they have been trained -- well-trained network
Externí odkaz:
http://arxiv.org/abs/2209.08678
Autor:
Micikevicius, Paulius, Stosic, Dusan, Burgess, Neil, Cornea, Marius, Dubey, Pradeep, Grisenthwaite, Richard, Ha, Sangwon, Heinecke, Alexander, Judd, Patrick, Kamalu, John, Mellempudi, Naveen, Oberman, Stuart, Shoeybi, Mohammad, Siu, Michael, Wu, Hao
FP8 is a natural progression for accelerating deep learning training inference beyond the 16-bit formats common in modern processors. In this paper we propose an 8-bit floating point (FP8) binary interchange format consisting of two encodings - E4M3
Externí odkaz:
http://arxiv.org/abs/2209.05433
A novel heuristic approach is proposed here for time series data analysis, dubbed Generalized weighted permutation entropy, which amalgamates and generalizes beyond their original scope two well established data analysis methods: Permutation entropy,
Externí odkaz:
http://arxiv.org/abs/2207.01169
Stock markets can become inefficient due to calendar anomalies known as day-of-the-week effect. Calendar anomalies are well-known in financial literature, but the phenomena remain to be explored in econophysics. In this paper we use multifractal anal
Externí odkaz:
http://arxiv.org/abs/2106.06164
Distance metric learning has attracted a lot of interest for solving machine learning and pattern recognition problems over the last decades. In this work we present a simple approach based on concepts from statistical physics to learn optimal distan
Externí odkaz:
http://arxiv.org/abs/2106.05495
Autor:
Stosic, Darko, Stosic, Dusan
While larger neural models are pushing the boundaries of what deep learning can do, often more weights are needed to train models rather than to run inference for tasks. This paper seeks to understand this behavior using search spaces -- adding weigh
Externí odkaz:
http://arxiv.org/abs/2105.12920
Autor:
Mishra, Asit, Latorre, Jorge Albericio, Pool, Jeff, Stosic, Darko, Stosic, Dusan, Venkatesh, Ganesh, Yu, Chong, Micikevicius, Paulius
As neural network model sizes have dramatically increased, so has the interest in various techniques to reduce their parameter counts and accelerate their execution. An active area of research in this field is sparsity - encouraging zero values in pa
Externí odkaz:
http://arxiv.org/abs/2104.08378
Stock market indices are one of the most investigated complex systems in econophysics. Here we extend the existing literature on stock markets in connection with nonextensive statistical mechanics. We explore the nonextensivity of price volatilities
Externí odkaz:
http://arxiv.org/abs/1901.07721
Autor:
STOSIC, Dusan
Publikováno v:
Repositório Institucional da UFPEUniversidade Federal de PernambucoUFPE.
Submitted by Isaac Francisco de Souza Dias (isaac.souzadias@ufpe.br) on 2016-07-13T19:23:52Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Dusan Stosic - dissertacao de mestrado.pdf: 6434406 bytes, che
Externí odkaz:
https://repositorio.ufpe.br/handle/123456789/17361
