Skip to contentSkip to filters

We use cookies for analytics.

From "Umwelt" to "World" models

Daniel Zoran

Google DeepMind

Recording

36 min

Abstract

Learning objects without supervision remains difficult outside restricted settings despite their central role in human vision. This talk argues that assumptions built into many object-centred models conflict with real-world data, making the usual problem formulation inadequate at scale. It examines that mismatch and presents ongoing work intended to support more meaningful learned representations.

Topics