Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Fernando Fernandes"'
Autor:
Siriwardhana, Shamane, McQuade, Mark, Gauthier, Thomas, Atkins, Lucas, Neto, Fernando Fernandes, Meyers, Luke, Vij, Anneketh, Odenthal, Tyler, Goddard, Charles, MacCarthy, Mary, Solawetz, Jacob
We conducted extensive experiments on domain adaptation of the Meta-Llama-3-70B-Instruct model on SEC data, exploring its performance on both general and domain-specific benchmarks. Our focus included continual pre-training (CPT) and model merging, a
Externí odkaz:
http://arxiv.org/abs/2406.14971
Efficiently post-training large language models remains a challenging task due to the vast computational resources required. We present Spectrum, a method that accelerates LLM training by selectively targeting layer modules based on their signal-to-n
Externí odkaz:
http://arxiv.org/abs/2406.06623
Autor:
Santos, Fernando Fernandes dos, Kritikakou, Angeliki, Condia, Josie Esteban Rodriguez, Balaguera, Juan David Guerrero, Reorda, Matteo Sonza, Sentieys, Olivier, Rech, Paolo
The reliability evaluation of Deep Neural Networks (DNNs) executed on Graphic Processing Units (GPUs) is a challenging problem since the hardware architecture is highly complex and the software frameworks are composed of many layers of abstraction. W
Externí odkaz:
http://arxiv.org/abs/2211.13094
RISC-V architectures have gained importance in the last years due to their flexibility and open-source Instruction Set Architecture (ISA), allowing developers to efficiently adopt RISC-V processors in several domains with a reduced cost. For applicat
Externí odkaz:
http://arxiv.org/abs/2206.08639
Autor:
Santos, Fernando Fernandes dos, Malde, Sujit, Cazzaniga, Carlo, Frost, Christopher, Carro, Luigi, Rech, Paolo
Publikováno v:
Nuclear & Space Radiation Effects Conference 2021
We investigate the sources of Detected Unrecoverable Errors (DUEs) in GPUs exposed to neutron beams. Illegal memory accesses and interface errors are among the more likely sources of DUEs. ECC increases the launch failure events. Our test procedure h
Externí odkaz:
http://arxiv.org/abs/2108.00554
Autor:
Neto, Fernando Fernandes, Solomon, Alemayehu Admasu, de Losso, Rodrigo, Garcia, Claudio, Cavalcanti, Pedro Delano
The aim of this paper is to discuss the use of Haar scattering networks, which is a very simple architecture that naturally supports a large number of stacked layers, yet with very few parameters, in a relatively broad set of pattern recognition prob
Externí odkaz:
http://arxiv.org/abs/1811.12081
Autor:
Neto, Fernando Fernandes
In this article we propose building general-purpose function approximators on top of Haar Scattering Networks. We advocate that this architecture enables a better comprehension of feature extraction, in addition to its implementation simplicity and l
Externí odkaz:
http://arxiv.org/abs/1804.03236
Autor:
Neto, Fernando Fernandes
The present paper aims to demonstrate the usage of Convolutional Neural Networks as a generative model for stochastic processes, enabling researchers from a wide range of fields (such as quantitative finance and physics) to develop a general tool for
Externí odkaz:
http://arxiv.org/abs/1801.03523