Abstract
Artificial Neural Networks (ANNs) have driven remarkable progress in AI over the past decade. Based on the ability of feature extraction and the Back Propagation (BP) supervision algorithm, ANNs can achieve outstanding performance in classification tasks. However, the dependence on data limits the application of ANNs in tasks with insufficient data. Spike Timing Dependent Plasticity (STDP) is widely believed to underlie the unsupervised learning process in the brain. Inspired by STDP, this paper presents a Phase-dependent plasticity (PDP) unsupervised learning algorithm. Combined with phase information, this method can introduce STDP into the ANNs. Our method can achieve a classification accuracy of 98.47% on the MSTAR dataset. PDP unsupervised algorithm is a practical attempt to combine ANNs with Spike Neural Networks (SNNs).
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
