2017/01/05 by Sadique Sheik, Sheik, Sadique, Somnath Paul +5
Engineering · Neuroscience · #Advanced Memory and Neural Computing #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function
paper · pdf · doi:10.48550/arxiv.1701.01495
openalex publication_date 2017/01/05 · openalex created_date 2022/10/05 · openalex updated_date 2026/07/28
Several learning rules for synaptic plasticity, that depend on either spike\ntiming or internal state variables, have been proposed in the past imparting\nvarying computational capabilities to Spiking Neural Networks. Due to design\ncomplications these learning rules are typically not implemented on\nneuromorphic devices leaving the devices to be only capable of inference. In\nthis work we propose a unidirectional post-synaptic potential dependent\nlearning rule that is only triggered by pre-synaptic spikes, and easy to\nimplement on hardware. We demonstrate that such a learning rule is functionally\ncapable of replicating computational capabilities of pairwise STDP. Further\nmore, we demonstrate that this learning rule can be used to learn and classify\nspatio-temporal spike patterns in an unsupervised manner using individual\nneurons. We argue that this learning rule is computationally powerful and also\nideal for hardware implementations due to its unidirectional memory access.\n