arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05636cs.LGcs.AIcs.NE
收藏

具有非线性耗散的时变电网络的梯度估计

A Gradient Estimator for Time-Varying Electrical Networks with Non-Linear Dissipation

Rain Neuromorphics(雷因神经形态公司)

Jack Kendall

摘要:

我们提出了一种方法,用于扩展技术的平衡传播的梯度估计在固定点神经网络更一般的设置有向,时变神经网络的建模电路。我们使用电路理论来构建一个拉格朗日能够描述深,有向神经网络建模使用非线性电容器和电感器,线性电阻器和源,以及一类特殊的非线性耗散元件称为分数忆阻器。然后,我们推导出一个估计的梯度的物理参数的网络,如突触电导,相对于一个任意的损失函数。这个估计器是完全本地的,因为它只依赖于每个突触本地可用的信息。最后,我们建议的方法,将这些结果扩展到网络的生物合理的神经元,如霍奇金-赫胥黎神经元。

英文摘要:

We propose a method for extending the technique of equilibrium propagation for estimating gradients in fixed-point neural networks to the more general setting of directed, time-varying neural networks by modeling them as electrical circuits. We use electrical circuit theory to construct a Lagrangian capable of describing deep, directed neural networks modeled using nonlinear capacitors and inductors, linear resistors and sources, and a special class of nonlinear dissipative elements called fractional memristors. We then derive an estimator for the gradient of the physical parameters of the network, such as synapse conductances, with respect to an arbitrary loss function. This estimator is entirely local, in that it only depends on information locally available to each synapse. We conclude by suggesting methods for extending these results to networks of biologically plausible neurons, e.g. Hodgkin-Huxley neurons.

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。

↑