Capsule Networks Explained
Craig discusses the evolution of capsule networks, highlighting the shift from supervised to unsupervised learning to enhance object recognition. He explains how capsules identify whole objects by analyzing parts and their relationships, and introduces the concept of dynamic routing to improve the accuracy of votes for potential object identities. This innovative approach aims to streamline the process of recognizing complex structures in visual data.In this clip
From this podcast
Eye on AI
Geoffrey Everest Hinton reviews his work in 2020 and talks about what he sees on the AI horizon
Related Questions