The Role of Short-Term Plasticity in Neuromorphic Learning: Learning from the Timing of Rate-Varying Events with Fatiguing Spike-Timing-Dependent Plasticity

Neural networks (NNs) have been able to provide record-breaking performance in several machine-learning tasks, such as image and speech recognition, natural-language processing, playing complex games, and data analytics for scientific or business purposes [1]. They process their inputs through a series of linear and nonlinear operations and use learning algorithms, i.e., rules that optimize the parameters of the network.