An adaptive learning approach for 3-D surface reconstruction from point clouds [0.03%]
一种基于点云的自适应学习三维表面重构方法
Agostinho de Medeiros Brito Junior,Adrião Duarte Dória Neto,Jorge Dantas de Melo et al.
Agostinho de Medeiros Brito Junior et al.
In this paper, we propose a multiresolution approach for surface reconstruction from clouds of unorganized points representing an object surface in 3-D space. The proposed method uses a set of mesh operators and simple rules for selective m...
Evaluation of the traffic parameters in a metropolitan area by fusing visual perceptions and CNN processing of webcam images [0.03%]
基于视觉感知和CNN处理的webcam图像的城市交通参数评估方法研究
Alberto Faro,Daniela Giordano,Concetto Spampinato
Alberto Faro
This paper proposes a traffic monitoring architecture based on a high-speed communication network whose nodes are equipped with fuzzy processors and cellular neural network (CNN) embedded systems. It implements a real-time mobility informat...
Automatic relevance determination for identifying thalamic regions implicated in schizophrenia [0.03%]
用于识别与精神分裂症有关的丘脑区域的自动相关性确定
Antony Browne,Angela Jakary,Sophia Vinogradov et al.
Antony Browne et al.
There have been many theories about and computational models of the schizophrenic disease state. Brain imaging techniques have suggested that abnormalities of the thalamus may contribute to the pathophysiology of schizophrenia. Several stud...
Ioan Buciu,Nikos Nikolaidis,Ioannis Pitas
Ioan Buciu
Plenty of methods have been proposed in order to discover latent variables (features) in data sets. Such approaches include the principal component analysis (PCA), independent component analysis (ICA), factor analysis (FA), etc., to mention...
Absolute exponential stability of recurrent neural networks with generalized activation function [0.03%]
具有一般激活函数的递归神经网络的绝对指数稳定性
Jun Xu,Yong-Yan Cao,Youxian Sun et al.
Jun Xu et al.
In this paper, the recurrent neural networks (RNNs) with a generalized activation function class is proposed. In this proposed model, every component of the neuron's activation function belongs to a convex hull which is bounded by two odd s...
Incremental learning of chunk data for online pattern classification systems [0.03%]
在线模式分类系统中的增量学习方法研究
Seiichi Ozawa,Shaoning Pang,Nikola Kasabov
Seiichi Ozawa
This paper presents a pattern classification system in which feature extraction and classifier learning are simultaneously carried out not only online but also in one pass where training samples are presented only once. For this purpose, we...
Representation of nonlinear random transformations by non-gaussian stochastic neural networks [0.03%]
非高斯随机神经网络中的非线性随机变换表示法
Claudio Turchetti,Paolo Crippa,Massimiliano Pirani et al.
Claudio Turchetti et al.
The learning capability of neural networks is equivalent to modeling physical events that occur in the real environment. Several early works have demonstrated that neural networks belonging to some classes are universal approximators of inp...
Hao Shen,Martin Kleinsteuber,Knut Huper
Hao Shen
The FastICA algorithm is one of the most prominent methods to solve the problem of linear independent component analysis (ICA). Although there have been several attempts to prove local convergence properties of FastICA, rigorous analysis is...
Adaptive gain control for spike-based map communication in a neuromorphic vision system [0.03%]
基于脉冲的神经形态视觉系统地图通信自适应增益控制
Yicong Meng,Bertram E Shi
Yicong Meng
To support large numbers of model neurons, neuromorphic vision systems are increasingly adopting a distributed architecture, where different arrays of neurons are located on different chips or processors. Spike-based protocols are used to c...
A constrained optimization approach to preserving prior knowledge during incremental training [0.03%]
基于增量学习中保护先验知识的约束优化方法
Silvia Ferrari,Mark Jensenius
Silvia Ferrari
In this paper, a supervised neural network training technique based on constrained optimization is developed for preserving prior knowledge of an input-output mapping during repeated incremental training sessions. The prior knowledge, refer...