Buscar
Mostrando ítems 1-10 de 58
Aplicação do Word2vec e do Gradiente descendente dstocástico em tradução automática
(2016-05-30)
O word2vec é um sistema baseado em redes neurais que processa textos e representa pa- lavras como vetores, utilizando uma representação distribuída. Uma propriedade notável são as relações semânticas encontradas nos modelos ...
A continuous-time model of stochastic gradient descent: convergence rates and complexities under Lojasiewicz inequality
(Universidad de Chile, 2021)
In this thesis we study the convergence rates and complexities of a continuous model of the Stochastic Gradient Descent (SGD) under convexity, strong convexity and Łojasiewicz assumptions, the latter being a way to generalize ...
Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
(2020)
Uniform stability is a notion of algorithmic stability that bounds the worst case change in the model output by the algorithm when a single data point in the dataset is replaced. An influential work of Hardt et al. [2016] ...
A Novel Approach on Visual Question Answering by Parameter Prediction using Faster Region Based Convolutional Neural Network
Visual Question Answering (VQA) is a stimulating process in the field of Natural Language Processing (NLP) and Computer Vision (CV). In this process machine can find an answer to a natural language question which is related ...
Treinamento de redes neurais com arquitetura multilayer perceptron em FPGA
(Florianópolis, SC, 2019-07-22)
Este trabalho de conclusão de curso apresenta uma implementação em Field Programmable Gate Arrays (FPGA) de um sistema responsável pelo treinamento on chip de redes neurais com arquitetura
Multilayer Perceptron (MLP). O ...
Sequential Monte Carlo with kernel embedded mappings: The mapping particle filter
(Academic Press Inc Elsevier Science, 2019-05)
In this work, a novel sequential Monte Carlo filter is introduced which aims at an efficient sampling of the state space. Particles are pushed forward from the prediction to the posterior density using a sequence of mappings ...
Stochastic neural networks
(Universidad Nacional de Colombia, 1991)
Artificial neural networks are brain-like models of parallel computations and cognitive phenomena. We sample some basic results about neural networks as they relate to stochastic and statistical processes. Given the explosivo ...
Métodos estocásticos de optimización
(Universidad de los AndesMatemáticasFacultad de CienciasDepartamento de Matemáticas, 2020)
The main purpose of this work is to study stochastic optimization methods used to minimize the problem of finite sums for convex functions. Within these methods, the method of gradient descent with mini-batch and the ...
Automatic determination of the learning rate for multivariate and multinomial regression models
Throughout the years, artificial intelligence has developed into a widely researched and applied field, as a result of the significant advancements in technology and the expansion in computer resources. Artificial intelligence ...