ML Meets Machine

  Machine learning

ML meets the Machine

Speakers: Lukáš Hudec, AI Architect @ Cognexa, Marek Šebo, Founder & Solution Designer @ Cognexa

Abstract: We will talk about building industrial inspection robots, which can detect defects that can be located anywhere on the surface and also within industrially produced goods. And discuss challenges such as:

  • How to run deep-learning-based detection on tens or hundreds of overlapping and fuzzy high-resolution images, returning a single ground truth
  • Which evaluation metrics really matter, and which don’t
  • How to integrate the AI system with the mechanics of a machine and also how to boost the detection accuracy by tuning optics
  • Best practices for including assisted annotation in the otherwise lengthy annotation process
  • How to prevent misdetections caused by optical artefacts, and how to detect almost invisible defects

Program: 17:30 Welcome chat 18:00 Talk 18:50 Discussion 19:10 Networking (Impact Hub)

There will be stream running on Facebook. You can join HERE.

About MLMUs: Machine Learning Meetups (MLMU) is an independent platform for people interested in Machine Learning, Information Retrieval, Natural Language Processing, Computer Vision, Pattern Recognition, Data Journalism, Artificial Intelligence, Agent Systems and all the related topics. MLMU is a regular community meeting usually consisting of a talk, a discussion and subsequent networking. Except of Prague, MLMU also spread to Brno, Bratislava and Košice.