Titlebook: Artificial Neural Networks and Machine Learning -- ICANN 2014; 24th International C Stefan Wermter,Cornelius Weber,Alessandro E. P. Vi Conf

fungus

书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014影响因子(影响力)




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014影响因子(影响力)学科排名




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014网络公开度




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014网络公开度学科排名




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014被引频次




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014被引频次学科排名




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014年度引用




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014年度引用学科排名




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014读者反馈




书目名称Artificial Neural Networks and Machine Learning -- ICANN 2014读者反馈学科排名

LATHE

Human Action Recognition with Hierarchical Growing Neural Gas Learningm depth map sequences. We then cluster pose-motion cues with a two-stream hierarchical architecture based on growing neural gas (GNG). Multi-cue trajectories are finally combined to provide prototypical action dynamics in the joint feature space. We extend the unsupervised GNG with two labelling fun

真实的你

Real-Time Anomaly Detection with a Growing Neural Gasnchronously operating pixels that is inspired by the human retina. Each pixel reports events of illumination changes, are processed in a purely event-based tracker that pursues edges of events in the input stream. The tracker estimates are used to determine whether the input events originate from an

倔强一点

尽忠

A Non-parametric Maximum Entropy Clustering quantities such as entropy and mutual information. Recently, since these quantities can be estimated in non-parametric manner, non-parametric information theoretic clustering gains much attention. Assuming the dataset is sampled from a certain cluster, and assigning different sampling weights depen

解脱

壁画

PLIC

Leaving Local Optima in Unsupervised Kernel Regressione local optima in the data space reconstruction error (DSRE) minimization process of unsupervised kernel regression (UKR). For this sake, we concentrate on a hybrid UKR variant that combines iterative solution construction with gradient descent based optimization. Patterns with high reconstruction e

诱骗

无聊的人