Buscar recursos académicos

We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two...

Materias / palabras clave: Claus process; Syngas; Acid gas; Process engineering; Hydrogen sulfide; Process (computing); Environmental science; Computer science; Work (physics); Sulfur dioxide; Natural gas; Sulfur

Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library...

Materias / palabras clave: Computer science; Artificial intelligence; Convolutional neural network; Image (mathematics); Pixel; Perception; Transformation (genetics); Ground truth; Transfer (computing); Computer vision; Pattern recognition (psycho...

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVR...

Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrar...

The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in proposal-based instance segmentation framew...

Previous article Next article An Algorithm for Least-Squares Estimation of Nonlinear ParametersDonald W. MarquardtDonald W. Marquardthttps://doi.org/10.1137/0111030PDFPDF PLUSBibTexSections ToolsAdd to favoritesExport Ci...

The discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construc...

Materias / palabras clave: brain-inspired computing, memristors, neuromorphic computing, artificial neural networks; Science: Mathematics: Instruments and machines: Electronic computers. Computer science

Materias / palabras clave: particle swarm optimization, artificial neural networks, neuro-fuzzy systems, machine learning, data mining, genetic programming; Technology: Electrical engineering. Electronics. Nuclear engineering: Electronics: Compute...

Materias / palabras clave: neural networks, fuzzy logic, eveolutionary computation, genetic algorithm, hybrid systems; Science: Science (General): Cybernetics; Science: Mathematics: Instruments and machines: Electronic computers. Computer science

Materias / palabras clave: fuzzy logic, neural networks, evolutionary and bio-inspired computation, learning theory, probability theory, hybrid methods; Technology: Technology (General): Industrial engineering. Management engineering: Information ...

Materias / palabras clave: intelligent systems, machine learning, neural computing, evolutionary computation, fuzzy systems, intelligent control and robotics; Science: Science (General): Cybernetics; Science: Mathematics: Instruments and machines:...

Materias / palabras clave: artificial neural networks, deep learning, neuromorphic computing, smart technologies, brain-inspired computing, data mining; Science: Physics; Science: Mathematics: Instruments and machines: Electronic computers. Comput...

Materias / palabras clave: evolutionary computation, soft computing, neural networks, fuzzy logic, optimization, bio-inspired robotics; Science: Mathematics: Instruments and machines: Electronic computers. Computer science