• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2017 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization >Fusion of deep learning architectures, multilayer feedforward networks and learning vector quantizers for deep classification learning
【24h】

Fusion of deep learning architectures, multilayer feedforward networks and learning vector quantizers for deep classification learning

机译：深度学习架构，多层前馈网络和用于深度分类学习的学习矢量量化器的融合

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The advantage of prototype based learning vector quantizers are the intuitive and simple model adaptation as well as the easy interpretability of the prototypes as class representatives for the class distribution to be learned. Although they frequently yield competitive performance and show robust behavior nowadays powerful alternatives have increasing attraction. Particularly, deep architectures of multilayer networks achieve frequently very high accuracies and are, thanks to modern graphic processor units use for calculation, trainable in acceptable time. In this conceptual paper we show, how we can combine both network architectures to benefit from their advantages. For this purpose, we consider learning vector quantizers in terms of feedforward network architectures and explain how it can be combined effectively with multilayer or single-layer feedforward network architectures. This approach includes deep and flat architectures as well as the popular extreme learning machines. For the resulting networks, the multi-/single-layer networks act as adaptive filters like in signal processing while the interpretability of the prototype-based learning vector quantizers is kept for the resulting filtered feature space. In this way a powerful combination of two successful architectures is obtained.
机译：基于原型的学习矢量量化器的优势在于直观，简单的模型适配以及易于理解的原型作为要学习的班级分布的班级代表。尽管它们经常产生有竞争力的表现并表现出强劲的行为，但如今，功能强大的替代产品的吸引力越来越大。特别地，多层网络的深层架构通常会达到很高的精度，并且由于使用了现代图形处理器单元进行计算，因此可以在可接受的时间内进行训练。在本概念文件中，我们展示了如何将两种网络体系结构结合起来以从它们的优势中受益。为此，我们考虑根据前馈网络体系结构学习矢量量化器，并解释如何将其与多层或单层前馈网络体系结构有效组合。这种方法包括深度和扁平架构以及流行的极限学习机。对于所得的网络，多层/单层网络像信号处理中一样充当自适应滤波器，同时针对所得的滤波后的特征空间保留基于原型的学习矢量量化器的可解释性。以这种方式，获得了两个成功架构的强大组合。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号