Pattern recognition with simple oscillating circuits
Pattern recognition with simple oscillating circuits
复制标题
DOI：
10.1088/1367-2630/13/7/073031
复制
发表时间：
2011-07-22
影响因子：
3.3
通讯作者：
Krischer, K.
中科院分区：
文献类型：
--
作者：
Hoelzel, R. W.;Krischer, K.
具有并行计算能力的神经网络设备通常很难构建，因为有大量的神经元-神经元连接。然而，存在一种理论方法(Hoppensteat和Izhikevich 1999 Phys.莱特牧师。82 2983)，放弃单个连接，只使用全局耦合：具有依赖时间的全局耦合的弱耦合振子系统能够以类似于Hopfield网络的联想方式执行模式识别。信息存储在各个振荡器的相移中。然而，到目前为止，甚至用这种耦合控制相移的可行性还没有在实验上得到证实。我们给出了这种神经网络装置的一个实验实现。它由八个正弦电范德波尔振荡器组成，它们通过一个以电势为耦合变量的可变电阻进行全局耦合。我们在实验中估计了位相耦合强度的有效值。为此，我们导出了一种通用的方法，允许人们相互比较不同的实验实现以及与相位方程模型进行比较。我们证明了振子的单个相移可以由弱的整体耦合来实验控制。此外，在提供失真输入图像的情况下，振荡网络确实可以从一组预定义图案中识别出正确的图像。因此，它可以用作关联存储设备的处理单元。
Neural network devices that inherently possess parallel computing capabilities are generally difficult to construct because of the large number of neuron-neuron connections. However, there exists a theoretical approach (Hoppensteadt and Izhikevich 1999 Phys. Rev. Lett. 82 2983) that forgoes the individual connections and uses only a global coupling: systems of weakly coupled oscillators with a time-dependent global coupling are capable of performing pattern recognition in an associative manner similar to Hopfield networks. The information is stored in the phase shifts of the individual oscillators. However, to date, even the feasibility of controlling phase shifts with this kind of coupling has not yet been established experimentally. We present an experimental realization of this neural network device. It consists of eight sinusoidal electrical van der Pol oscillators that are globally coupled through a variable resistor with the electric potential as the coupling variable. We estimate an effective value of the phase coupling strength in our experiment. For that, we derive a general approach that allows one to compare different experimental realizations with each other as well as with phase equation models. We demonstrate that individual phase shifts of oscillators can be experimentally controlled by a weak global coupling. Furthermore, supplied with a distorted input image, the oscillating network can indeed recognize the correct image out of a set of predefined patterns. It can therefore be used as the processing unit of an associative memory device.