Modeling the Dynamics of Spiking Networks with Memristor-Based STDP to Solve Classification Tasks
The problem with training spiking neural networks (SNNs) is relevant due to the ultra-low power consumption these networks could exhibit when implemented in neuromorphic hardware. The ongoing progress in the fabrication of memristors, a prospective basis for analogue synapses, gives relevance to stu...
Main Authors: | Alexander Sboev, Danila Vlasov, Roman Rybka, Yury Davydov, Alexey Serenko, Vyacheslav Demin |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/9/24/3237 |
Similar Items
-
Comparison of Bagging and Sparcity Methods for Connectivity Reduction in Spiking Neural Networks with Memristive Plasticity
by: Roman Rybka, et al.
Published: (2024-02-01) -
Memristive Spiking Neural Networks Trained with Unsupervised STDP
by: Errui Zhou, et al.
Published: (2018-12-01) -
STDP-Driven Rewiring in Spiking Neural Networks under Stimulus-Induced and Spontaneous Activity
by: Sergey A. Lobov, et al.
Published: (2023-07-01) -
Neuron Circuit Failure and Pattern Learning in Electronic Spiking Neural Networks
by: Sumedha Gandharava, et al.
Published: (2022-04-01) -
Hardware Demonstration of SRDP Neuromorphic Computing with Online Unsupervised Learning Based on Memristor Synapses
by: Ruiyi Li, et al.
Published: (2022-03-01)