Spin-NeuroMem: An Energy-Efficient Neuromorphic Associative Memory Design Leveraging Spintronic Devices
Spin-NeuroMem is a low-power neuromorphic associative memory design that integrates spintronic devices and CMOS components, achieving superior performance in terms of power consumption, area, and recall speed compared to prior works.
Dynamically Reconfigurable Stochastic Neurons Enabled by Strain-Engineered Low Barrier Nanomagnets
Strain-mediated control of the energy barrier height in low barrier nanomagnets enables reconfiguring binary stochastic neurons (BSNs) to analog stochastic neurons (ASNs) and vice versa, enabling a wide range of applications in neuromorphic hardware.
Photonic-Electronic Spiking Neuron for High-Speed Neuromorphic Sensing and Computing
Photonic-electronic spiking neurons offer high-speed, energy-efficient neuromorphic sensing and computing capabilities.
Hardware in Loop Learning with Spin Stochastic Neurons: A Detailed Analysis
Hardware-in-loop learning with spin stochastic neurons showcases the potential for edge-intelligent devices.
Mem-Elemente basierte Neuromorphe Hardware für neuronale Netzwerkanwendungen
Die Integration von Mem-Elementen in neuromorphe Hardware bietet eine vielversprechende Lösung für energieeffiziente und leistungsstarke neuronale Netzwerkanwendungen.
VPRTempo: A Fast Spiking Neural Network for Visual Place Recognition
Spiking Neural Networks offer fast and efficient solutions for Visual Place Recognition tasks, enabling real-time deployment on resource-constrained robotic systems.
Effizientes Event-Driven Lernen für Spiking-Neuronale Netzwerke
Effektive Event-Driven Lernalgorithmen für tiefe SNNs.
Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization
Optimizing ANN-SNN conversion for lossless results under ultra-low latency.
Spike-based Neuromorphic Computing for Enhanced Computer Vision Insights
Enhancing computer vision through spike-based neuromorphic computing.
Deep Unsupervised Learning Using Spike-Timing-Dependent Plasticity: A Novel Approach for Training Spiking Neural Networks
A novel Deep-STDP framework enhances unsupervised learning in Spiking Neural Networks, outperforming traditional clustering methods.
