Building SNN application for Neuromorphic HWs

SynSense is a Nueromorphic startup founded in 2018 with offices in Zurich and China. We have two family of SNN processors: Xylo for low dimensional signal processing and Speck for vision processing. Both HWs come with open source and user friendly python-based librarys: Rockpool and sinabs that have been co designed with HWs. 


In an initial tutorial I will present the pipeline (from design and training of the network to deployment on HW) and the goal is to create a workgroup with interested people to build SNN applications.


SynSense opensource librarys :




Install required packages for the tutorial:


  • pip install --quiet rockpool matplotlib torch tonic rich jax jaxlib xylosim samna bitstruct



example datasets for audio classification with Xylo:



  • https://dcase.community/challenge2016/task-sound-event-detection-in-synthetic-audio

  • https://dcase.community/challenge2023/task-low-complexity-acoustic-scene-classification 


 

Go to group wiki Go to wiki users Info

Timetable

Day Time Location
Tue, 30.04.2024 21:00 - 22:00 arcade

Moderator

Mina Khoei

Members

Muhammad Aitsam
Sirine Arfa
Gabriel Béna
Filippo Costa
Santiago Díaz Romero
Jesse Hagenaars
Marzieh Hassanshahi varposhti
Sanja Karilanova
Yulia Sandamirskaya
Thomas Shoesmith