Improving scalability of ART neural networks

详细信息    查看全文

• 作者：Fernando Benites ; ^{Fernando.Benites@uni-konstanz.de}Author Vitae ; Elena Sapozhnikova ^{Elena.Sapozhnikova@uni-konstanz.de}Author Vitae
• 关键词：Neural networks ; Adaptive resonance theory ; Clustering ; Classification ; Multi-label classification
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：22 March 2017
• 年：2017
• 卷：230
• 期：Complete
• 页码：219-229
• 全文大小：709 K
• 卷排序：230

文摘

With the increasing amount of available data, the need for classification of large data volumes is permanently growing. In order to cope with this challenge, neural classifiers should be adapted to large-scale data. We present here a well scalable extension to the fuzzy Adaptive Resonance Associative Map (ARAM) neural network, which was specially developed for the quick classification of high-dimensional and large data. This extension aims at increasing the classification speed by adding an extra layer for clustering learned prototypes into large clusters. This enables the activation of only one or a few clusters i.e. a small fraction of all prototypes, reducing the classification time significantly. Further we introduce two methods to adapt this extension to a multi-label classification task.