BriefGPT.xyz
Jan, 2013
DeSTIN中的循环在线聚类作为时空特征提取器
Recurrent Online Clustering as a Spatio-Temporal Feature Extractor in DeSTIN
HTML
PDF
Steven R. Young, Itamar Arel
TL;DR
该论文提出了一种基于状态信息反馈的机制来替换传统的计算转移表的深度学习体系结构的改进方法，该方法在空间输入和当前状态中进行聚类，取得了MNIST分类基准测试的最优结果。
Abstract
This paper presents a basic enhancement to the DeSTIN architecture. It replaces the explicitly calculated
transition tables
that are used to capture
temporal features
with a simpler, more scalable mechanism. This
→