Training spiking networks with hybrid ann-snn conversion and spike-based backpropagation
-
Updated
Apr 4, 2021 - Python
E5E8
Training spiking networks with hybrid ann-snn conversion and spike-based backpropagation
Conversion from CNNs to SNNs using Tensorflow-Keras
Hardware-verified SNN-equivalent intrusion detection system (IDS) on STM32N6 Neural-ART NPU. INT8 quantized MLP achieving 0.4561ms inference at 800MHz. First publicly documented IDS on a commodity MCU NPU with T=1 SNN-ANN equivalence validation.
Add a description, image, and links to the ann-snn-conversion topic page so that developers can more easily learn about it.
To associate your repository with the ann-snn-conversion topic, visit your repo's landing page and select "manage topics."