Fiete Ila R, Seung H Sebastian
Kavli Institute for Theoretical Physics, University of California, Santa Barbara, California 93106, USA.
Phys Rev Lett. 2006 Jul 28;97(4):048104. doi: 10.1103/PhysRevLett.97.048104.
We present a method of estimating the gradient of an objective function with respect to the synaptic weights of a spiking neural network. The method works by measuring the fluctuations in the objective function in response to dynamic perturbation of the membrane conductances of the neurons. It is compatible with recurrent networks of conductance-based model neurons with dynamic synapses. The method can be interpreted as a biologically plausible synaptic learning rule, if the dynamic perturbations are generated by a special class of "empiric" synapses driven by random spike trains from an external source.
我们提出了一种关于估计目标函数相对于脉冲神经网络突触权重的梯度的方法。该方法通过测量目标函数响应神经元膜电导的动态扰动时的波动来起作用。它与具有动态突触的基于电导模型神经元的递归网络兼容。如果动态扰动是由一类特殊的由来自外部源的随机脉冲序列驱动的“经验性”突触产生的，那么该方法可以被解释为一种生物学上合理的突触学习规则。
