Self-Organising Temporal Pooling

被引：0

作者：

Slack, Daniel ^{[1
]}

McCane, Brendan ^{[1
]}

Knott, Alistair ^{[1
]}

机构：

[1] Univ Otago, Dept Comp Sci, Dunedin, New Zealand

来源：

2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | 2017年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Temporal Pooling (TP) is a recent technique for processing temporal events by forming declarative representations of the complete sequences. In this paper, we examine and extend the functionality of the existing TP algorithm from the Hierarchical Temporal Memory (HTM) framework and introduce the Self-Organising Temporal Pooling (SOTP) architecture. The SOTP draws together the Merge Self-Organising Map (MSOM) and a new algorithm termed the Modified Temporal Pooler (MTP) to produce functionality not yet seen in a TP. This new architecture is shown to be capable of producing stable declarative representations of sequences that activate consistently for each item in that sequence.

引用

页码：4316 / 4323

页数：8