4th MunichNeuromorphic Hackathon

The hackathon lets participants dive into real-world applications of neuromorphic computing, a brain-inspired paradigm for artificial intelligence that mimics the structure and dynamics of biological neural systems. Unlike conventional deep learning, neuromorphic approaches offer radical energy efficiency and temporal processing capabilities that are reshaping the edge AI landscape.

Challenges.

Each challenge is brought by a research lab or industry partner. Teams pick a track on day one and work on it for the whole event, under the supervision of expert neuromorphic engineers and topic providers.

Many challenges from previous editions have stuck with their teams beyond the event, with work continuing well after the hackathon ended. Two have so far led to peer-reviewed publications at top conferences:

1. [1]Scaling Up Resonate-and-Fire Networks for Fast Deep Learning
2. [2]Efficient Onboard Spacecraft Pose Estimation with Event Cameras and Neuromorphic Hardware

A multi-day event.

An overview of how the hackathon week unfolds. Detailed times will be confirmed closer to the event.