Sketchnotes from TWiML&AI #111: Learning “Common Sense” and Physical Concepts with Roland Memisevic

These are my sketchnotes for Sam Charrington’s podcast This Week in Machine Learning and AI about Learning “Common Sense” and Physical Concepts with Roland Memisevic:

Sketchnotes from TWiMLAI talk #111: Learning “Common Sense” and Physical Concepts with Roland Memisevic

You can listen to the podcast here.

In today’s episode, I’m joined by Roland Memisevic, co-founder, CEO, and chief scientist at Twenty Billion Neurons. Roland joined me at the RE•WORK Deep Learning Summit in Montreal to discuss the work his company is doing to train deep neural networks to understand physical actions. In our conversation, we dig into video analysis and understanding, including how data-rich video can help us develop what Roland calls comparative understanding, or AI “common sense”. We briefly touch on the implications of AI/ML systems having comparative understanding, and how Roland and his team are addressing problems like getting properly labeled training data. https://twimlai.com/twiml-talk-111-learning-common-sense-physical-concepts-roland-memisevic/