Core Concepts
Spiking Neural Networks (SNNs) require efficient simulators for real-time interaction and analysis to optimize performance and parameter tuning.
Abstract
Standalone Note here
INTRODUCTION
Spike timing crucial for neural computations, driving SNN development.
SNNs energy-efficient but complex to implement due to neural structures.
Cutting-edge simulators like Brian2, NEST, CARLsim designed for brain function study.
PROJECT DESCRIPTION
Analyzing resource-efficient implementations of biologically inspired SNNs.
Focus on computer vision applications like object detection/recognition.
Utilizing CPU-based multi-core architecture for performance maximization.
Importance of understanding input-output concentration parameters for precise simulations.
FUTURE DIRECTIONS
RAVSim allows real-time interaction with SNN simulation for parameter extraction.
Balancing parametric values crucial for stable SNN model output.
RAVSim offers a user-friendly alternative to code-based experiments.
DATA AVAILABILITY AND ACKNOWLEDGEMENTS
RAVSim is open-source and available on LabVIEW's official website.
Research supported by the research training group "Dataninja" and project SAIL.
REFERENCES
Grüning & Bohte (2014): Spiking neural networks: Principles and challenges.
Stimberg et al. (2019): Brian 2, an intuitive and efficient neural simulator.
Eppler et al. (2009): PyNEST: a convenient interface to the nest simulator.
Stats
NICE, 11 – 14 April, 2023,
LabVIEW: https://www.ni.com/de-de/shop/labview.html