5 papers
An Optimization Framework for Automated Assessment of Biological Plausibility of Spiking Neurons
Sven Nitzsche, Alexandru Ionita, Andreas Faust +2
Biological plausibility is a key concept in neuromorphic computing and spiking neural networks, yet it remains inconsistently defined and difficult to quantify. In this work, we pr…
Zero-Inflated Gaussian Distributions Enable Parameter-Space Sparsity in Estimation-of-Distribution Algorithms
Andreas Faust, Sven Nitzsche, Juergen Becker
Estimation-of-distribution algorithms (EDAs) are a powerful class of evolutionary methods for black-box optimization, especially when little is known about the structure of the obj…
YANA: Bridging the Neuromorphic Simulation-to-Hardware Gap
Brian Pachideh, Sven Nitzsche, Moritz Neher +5
Spiking Neural Networks (SNNs) promise significant advantages over conventional Artificial Neural Networks (ANNs) for applications requiring real-time processing of temporally spar…
Spiking Neural Networks for Low-Power Vibration-Based Predictive Maintenance
Alexandru Vasilache, Sven Nitzsche, Christian Kneidl +3
Advancements in Industrial Internet of Things (IIoT) sensors enable sophisticated Predictive Maintenance (PM) with high temporal resolution. For cost-efficient solutions, vibration…
A PyTorch-Compatible Spike Encoding Framework for Energy-Efficient Neuromorphic Applications
Alexandru Vasilache, Jona Scholz, Vincent Schilling +4
Spiking Neural Networks (SNNs) offer promising energy efficiency advantages, particularly when processing sparse spike trains. However, their incompatibility with traditional datas…