当前位置: X-MOL 学术Phys. D Nonlinear Phenom. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
The echo index and multistability in input-driven recurrent neural networks
Physica D: Nonlinear Phenomena ( IF 2.7 ) Pub Date : 2020-06-22 , DOI: 10.1016/j.physd.2020.132609
Andrea Ceni , Peter Ashwin , Lorenzo Livi , Claire Postlethwaite

A recurrent neural network (RNN) possesses the echo state property (ESP) if, for a given input sequence, it “forgets” any internal states of the driven (nonautonomous) system and asymptotically follows a unique, possibly complex trajectory. The lack of ESP is conventionally understood as a lack of reliable behaviour in RNNs. Here, we show that RNNs can reliably perform computations under a more general principle that accounts only for their local behaviour in phase space. To this end, we formulate a generalisation of the ESP and introduce an echo index to characterise the number of simultaneously stable responses of a driven RNN. We show that it is possible for the echo index to change with inputs, highlighting a potential source of computational errors in RNNs due to characteristics of the inputs driving the dynamics.



中文翻译:

输入驱动的递归神经网络中的回声指数和多重稳定性

如果对于给定的输入序列,递归神经网络(RNN)“忘记”了驱动(非自治)系统的任何内部状态,并且渐近地遵循唯一的,可能是复杂的轨迹,则它具有回波状态属性(ESP)。传统上将ESP的缺乏理解为RNN中缺乏可靠的行为。在这里,我们表明RNN可以在更通用的原则下可靠地执行计算,该原则仅考虑其在相空间中的局部行为。为此,我们制定了ESP的概括,并引入了回波索引来表征驱动RNN的同时稳定响应的数量。我们表明,回波索引可能随输入而变化,这突出了由于驱动动力学的输入特性而导致的RNN中计算错误的潜在来源。

更新日期:2020-06-22
down
wechat
bug