Buscar recursos académicos

"Bipartite graphs have received some attention in the study of social networks and of biological mutualistic systems. A generalization of a previous model is presented, that evolves the topology of the graph in order t...

"Data-driven simulation of pedestrian dynamics is an incipient and promising approach for building reliable microscopic pedestrian models. We propose a methodology based on generalized regression neural networks, which d...

"Data-driven simulation of pedestrian dynamics is an incipient and promising approach for building reliable microscopic pedestrian models. We propose a methodology based on generalized regression neural networks, which d...

Images compression is a widely studied topic. Conventional situations offer variable compression ratios depending on the image in question and, in general, do not yield good results for images that are rich in tones. Thi...

The proposal of this research line is the search for alternatives to the resolution of complex problems where human knowledge should be apprehended in a general fashion. In particular, the activities developed so far can...

We propose a technique for producing `visual explanations' for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent. Our approach - Gradient-weighted Class Activat...

Abstract This book provides the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition. After introducing the basic concepts of pattern recognition, the book...

Fast response, storage efficiency, fault tolerance and graceful degradation in face of scarce or spurious inputs make neural networks appropiate tools for Intelligent Computer Systems. But on the other hand, learning alg...

This article presents the empirical evaluation of several simple metaheuristics applied to solve the Generalized Steiner Problem (GSP). This problem models the design of high-reliability communication networks, demanding...

The exponential periodicity and stability of continuous nonlinear neural networks with variable coefficients and distributed delays are investigated via employing Young inequality technique and Lyapunov method. Some new...

Networking together hundreds or thousands of cheap microsensor nodes allows users to accurately monitor a remote environment by intelligently combining the data from the individual nodes. These networks require robust wi...

In this paper, we discuss consensus problems for networks of dynamic agents with fixed and switching topologies. We analyze three cases: 1) directed networks with fixed topology; 2) directed networks with switching topol...

From the Publisher: This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition. After introducing the basic concepts, the book examines techniques fo...

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 central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local re...

Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local receptive fields. In order to boost the rep...

Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Recti...

"Real world scenarios are increasingly being represented with graph databases. Networks in general, and social networks in particular, can be represented as node in a graph, linked through edges. When relationships and n...

"We investigate the role of connection density in an adaptive network model of chaotic units that dynamically rewire based on their internal states and local coherence. By systematically varying the network's connectivit...

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...

Bowling Alone: America’s Declining Social Capital Robert D. Putnam (bio) Many students of the new democracies that have emerged over the past decade and a half have emphasized the importance of a strong and active civi...

Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather tha...

List of Boxes List of Tables and Figures Foreword Acknowledgments 1. Defining Content Analysis Is Content Analysis Easy? Is It Something That Anyone Can Do? A Six-Part Definition of Content Analysis 2. Milestones in the ...

Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progres...