Add to ORKGEn este estudio analizo el proceso de entrenamiento de una red neural convolucional desde la perspectiva del rendimiento computacional. Mediante el uso de herramientas de instrumentación y métricas de eficiencia, voy a mostrar cómo se comporta este programa en un entorno de alta capacidad computacional usando distintos conjuntos de datos. Además, mostraré varios test de rendimiento relacionados con la escalabilidad de recursos y un estudio sobre cómo algunos parámetros de ejecución alteran los resultados.In this study I analyse the training process of a convolutional neural network from a computational performance perspective. By using instrumentation tools and efficiency metrics, I will show how this kind of programs behave in a high perfo...
Emerging applications such as Deep Learning are often data-driven, thus traditional approaches based...
Thesis (Master of Science in Informatics)--University of Tsukuba, no. 36020, 2016.3.25201
Indiana University-Purdue University Indianapolis (IUPUI)Performance models are useful as mathematic...
Performance modelling for scalable deep learning is very important to quantify the efficiency of la...
The objective of this report is to implement a Convolutional Neural Network (CNN) in an FPGA, with a...
Convolutional Neural Networks (CNNs) trained through backpropagation are central to several, competi...
Motivated by the usefulness of high resolution images in a broad range of applications, such as medi...
As the amount of information available for data mining grows larger, the amount of time needed to tr...
Convolutional Neural Networks (CNNs) are biologically inspired feed forward artificial neural networ...
Developing software for exascale systems will become even more challenging than for today’s systems...
In many machine learning applications, interpretability is of the utmost importance. Artificial inte...
Graphs are a common representation in many problem domains, including engineering, finance, medicine...
Deep Neural Networks (DNN), specifically Convolutional Neural Networks (CNNs) are often associated w...
Optimized software implementations of artificial neural networks leverage primitives from performanc...
Deep learning contains a set of algorithms that are based on the functioning of human brain i.e. neu...
Emerging applications such as Deep Learning are often data-driven, thus traditional approaches based...
Thesis (Master of Science in Informatics)--University of Tsukuba, no. 36020, 2016.3.25201
Indiana University-Purdue University Indianapolis (IUPUI)Performance models are useful as mathematic...
Performance modelling for scalable deep learning is very important to quantify the efficiency of la...
The objective of this report is to implement a Convolutional Neural Network (CNN) in an FPGA, with a...
Convolutional Neural Networks (CNNs) trained through backpropagation are central to several, competi...
Motivated by the usefulness of high resolution images in a broad range of applications, such as medi...
As the amount of information available for data mining grows larger, the amount of time needed to tr...
Convolutional Neural Networks (CNNs) are biologically inspired feed forward artificial neural networ...
Developing software for exascale systems will become even more challenging than for today’s systems...
In many machine learning applications, interpretability is of the utmost importance. Artificial inte...
Graphs are a common representation in many problem domains, including engineering, finance, medicine...
Deep Neural Networks (DNN), specifically Convolutional Neural Networks (CNNs) are often associated w...
Optimized software implementations of artificial neural networks leverage primitives from performanc...
Deep learning contains a set of algorithms that are based on the functioning of human brain i.e. neu...
Emerging applications such as Deep Learning are often data-driven, thus traditional approaches based...
Thesis (Master of Science in Informatics)--University of Tsukuba, no. 36020, 2016.3.25201
Indiana University-Purdue University Indianapolis (IUPUI)Performance models are useful as mathematic...