arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.04126cs.NEcs.AIcs.LG
收藏

时间权重

Temporal Weights

College of Information and Computer Sciences(信息与计算机科学学院);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Adam Kohan, Ed Rietman, Hava Siegelmann

摘要:

在人工神经网络中,权重是突触的静态表示。然而,突触不是静态的,它们随着时间的推移有自己的相互作用动态。为了将权重与相互作用的动力学相结合,我们使用了一个描述同步的模型,该模型能够随着时间的推移捕获一系列神经和一般生物现象的核心机制。这些时间权重(TW)的理想拟合是神经ODE,具有连续动态和对时间的依赖性。由此产生的递归神经网络通过计算序列的排序以及时间的长度和规模来有效地对时间动态进行建模。通过向模型添加时间权重,我们在稀疏、不规则采样的时间序列数据集上展示了更好的性能、更小的模型和数据效率。

英文摘要:

In artificial neural networks, weights are a static representation of synapses. However, synapses are not static, they have their own interacting dynamics over time. To instill weights with interacting dynamics, we use a model describing synchronization that is capable of capturing core mechanisms of a range of neural and general biological phenomena over time. An ideal fit for these Temporal Weights (TW) are Neural ODEs, with continuous dynamics and a dependency on time. The resulting recurrent neural networks efficiently model temporal dynamics by computing on the ordering of sequences, and the length and scale of time. By adding temporal weights to a model, we demonstrate better performance, smaller models, and data efficiency on sparse, irregularly sampled time series datasets.

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。

↑