Hands-On Worshop – Presentation of Faster AI
June 23 at 12 h 00 min - 16 h 00 min
FasterAI Labs is a UMons spinoff project specialized in compressing AI models for production deployment. They help engineering teams deploy faster, lighter models on edge hardware (NVIDIA Jetson, mobile NPUs, edge CPUs) using pruning, quantization, and knowledge distillation.In this hands-on workshop, you’ll work directly with their compression toolchain on a real vision model. By the end of the session, you’ll have run a model through the FasterAI engine, measured the size, latency, and energy reduction on a target chip, and walked away with a reproducible recipe to apply to your own models.Hosted by Nathan Hubens, founder of FasterAI Labs (PhD in neural network compression with 8+ years of public open-source work). The workshop is designed for ML engineers, technical leads, and AI deployment owners working on edge or on-prem inference.
📅 Tuesday, 23 June 2026⏰ From 12:00 to 16:00 (lunch included)📍Click – Mons