Short Term Plasticity

Short-term plasticity (STP) refers to the rapid, transient changes in synaptic strength that influence neuronal communication and information processing. Current research focuses on incorporating STP mechanisms, particularly in spiking neural networks (SNNs), using models like STP neurons (STPNs) and algorithms incorporating adaptive synaptic filters and thresholds, to improve the efficiency and performance of artificial neural networks. This work aims to better understand how STP contributes to learning and memory in biological systems and to leverage these insights for developing more biologically plausible and energy-efficient artificial intelligence. The resulting advancements have the potential to improve machine learning algorithms across various applications, from robotics to video game AI.

Papers

July 6, 2022

An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections
Yiting Dong, Dongcheng Zhao, Yang Li, Yi Zeng
New Connection Spike Timing Dependent Plasticity Synaptic Plasticity Plausible Learning Short Term Plasticity

June 28, 2022

Short-Term Plasticity Neurons Learning to Learn and Forget
Hector Garcia Rodriguez, Qinghai Guo, Timoleon Moraitis
Recurrent Unit Short Term Plasticity

March 29, 2022

Spatiotemporal Patterns in Neurobiology: An Overview for Future Artificial Intelligence
Sean Knight, Navjot Gadda
Neural Field Computational Model Neuroscience Research Spatiotemporal Pattern Future AI System Neural Network Application Neuronal Heterogeneity Short Term Plasticity

Short Term Plasticity

Papers

An Unsupervised STDP-based Spiking Neural Network Inspired By Biologically Plausible Learning Rules and Connections

Short-Term Plasticity Neurons Learning to Learn and Forget

Spatiotemporal Patterns in Neurobiology: An Overview for Future Artificial Intelligence