Rudner Tamás, Porod Wolfgang, Csaba Gyorgy
Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Budapest, Hungary.
Department of Electrical Engineering, University of Notre Dame (NDnano), Notre Dame, IN, United States.
Front Neurosci. 2024 Mar 4;18:1307525. doi: 10.3389/fnins.2024.1307525. eCollection 2024.
We demonstrate the utility of machine learning algorithms for the design of oscillatory neural networks (ONNs). After constructing a circuit model of the oscillators in a machine-learning-enabled simulator and performing (BPTT) for determining the coupling resistances between the ring oscillators, we demonstrate the design of associative memories and multi-layered ONN classifiers. The machine-learning-designed ONNs show superior performance compared to other design methods (such as Hebbian learning), and they also enable significant simplifications in the circuit topology. We also demonstrate the design of multi-layered ONNs that show superior performance compared to single-layer ones. We argue that machine learning can be a valuable tool to unlock the true computing potential of ONNs hardware.
我们展示了机器学习算法在振荡神经网络（ONN）设计中的效用。在支持机器学习的模拟器中构建振荡器的电路模型，并执行反向传播通过时间（BPTT）以确定环形振荡器之间的耦合电阻后，我们展示了关联存储器和多层ONN分类器的设计。与其他设计方法（如赫布学习）相比，机器学习设计的ONN表现出卓越的性能，并且它们还能显著简化电路拓扑结构。我们还展示了与单层ONN相比性能更优的多层ONN的设计。我们认为机器学习可以成为释放ONN硬件真正计算潜力的宝贵工具。
