arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1708.06004cs.NE
收藏

时间序列玻尔兹曼机

Boltzmann machines for time-series

Takayuki Osogami

摘要:

我们回顾玻尔兹曼机扩展的时间序列。这些模型通常具有递归结构,并且通过时间反向传播(BPTT)来学习它们的参数。然而,在线学习中BPTT的每步计算复杂性相对于先前时间序列的长度线性增长(即,学习规则在时间上不是局部的),这限制了BPTT在在线学习中的适用性。然后,我们回顾动态玻尔兹曼机(DyBM),其学习规则是本地的时间。DyBM的学习规则涉及尖峰定时依赖可塑性(STDP),其已经被生物神经网络假设和实验证实。

英文摘要:

We review Boltzmann machines extended for time-series. These models often have recurrent structure, and back propagration through time (BPTT) is used to learn their parameters. The per-step computational complexity of BPTT in online learning, however, grows linearly with respect to the length of preceding time-series (i.e., learning rule is not local in time), which limits the applicability of BPTT in online learning. We then review dynamic Boltzmann machines (DyBMs), whose learning rule is local in time. DyBM's learning rule relates to spike-timing dependent plasticity (STDP), which has been postulated and experimentally confirmed for biological neural networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑