Buscar recursos académicos

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are t...

The optimization of nonlinear functions using particle swarm methodology is described. Implementations of two paradigms are discussed and compared, including a recently developed locally oriented paradigm. Benchmark test...

Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a n...

Today, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advanta...

The caret package, short for classification and regression training, contains numerous tools for developing predictive models using the rich set of models available in R. The package focuses on simplifying model training...

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In...

It is shown by an extensive benchmark on molecular energy data that the mathematical form of the damping function in DFT-D methods has only a minor impact on the quality of the results. For 12 different functionals, a st...

Materias / palabras clave: Extreme learning machine; Computer science; Bottleneck; Generalization; Feedforward neural network; Artificial neural network; Benchmark (surveying); Feed forward; Artificial intelligence; Key (lock); Machine learning; A...

Materias / palabras clave: Parallel computing; Computer science; Benchmark (surveying); Parallel algorithm; Intel iPSC; Algorithm; Range (aeronautics); Molecular dynamics; Supercomputer; Node (physics); Computational science; Physics

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors that are based on deep convolutional netwo...

Materias / palabras clave: Benchmark (surveying); Artificial intelligence; Computer science; Categorical variable; Cognitive neuroscience of visual object recognition; Scale (ratio); Object (grammar); Object detection; Field (mathematics); Pattern...

Materias / palabras clave: Computational intelligence; Support vector machine; Least squares support vector machine; Quadratic programming; Benchmark (surveying); Set (abstract data type); Computer science; Quadratic equation; Mathematics; Artific...

A multiple sequence alignment program, MAFFT, has been developed. The CPU time is drastically reduced as compared with existing methods. MAFFT includes two novel techniques. (i) Homo logous regions are rapidly identified...

We describe MUSCLE, a new computer program for creating multiple alignments of protein sequences. Elements of the algorithm include fast distance estimation using kmer counting, progressive alignment using a new profile ...

A concept for the optimization of nonlinear functions using particle swarm methodology is introduced. The evolution of several paradigms is outlined, and an implementation of one of the paradigms is discussed. Benchmark ...

Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid p...

SUMMARY: Limitations of genome sequencing techniques have led to dozens of assembly algorithms, none of which is perfect. A number of methods for comparing assemblers have been developed, but none is yet a recognized ben...

Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains ...

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where th...

Materias / palabras clave: Generalization; Feature vector; Support vector machine; Artificial intelligence; Computer science; Relevance vector machine; Dimension (graph theory); Structured support vector machine; Feature (linguistics); Benchmark (...

Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning....

Materias / palabras clave: Pascal (unit); Benchmark (surveying); Artificial intelligence; Computer science; Object detection; Cognitive neuroscience of visual object recognition; Machine learning; Visual inspection; Context (archaeology); Object (...

Materias / palabras clave: Softmax function; Computer science; Benchmark (surveying); Classifier (UML); Artificial intelligence; Convolutional neural network; Machine learning; Visualization; Pattern recognition (psychology); Geodesy; Geography

Multiagent Systems is the title of a collection of papers dedicated to surveying specific themes of Multiagent Systems (MAS) and Distributed Artificial Intelligence (DAI). All of them authored by leading researchers of t...