Personal tools
You are here: Home Events ANC Workshop: Charlie Nash, Chair: Heru Praptono

ANC Workshop: Charlie Nash, Chair: Heru Praptono

— filed under:

  • ANC Workshop Talk
When Feb 20, 2018
from 11:00 AM to 12:00 PM
Where IF 4.31/4.33
Add event to calendar vCal


The Multi-Entity Variational Autoencoder


Representing the world as objects is core to human intelligence. It is the basis of people’s sophisticated capacities for reasoning, imagining, planning, and learning. Artificial intelligence typically assumes human-defined representations of objects, and little work has explored how object-based representations can arise through unsupervised learning. Here we present an approach for learning probabilistic, object-based representations from data, called the “multi-entity variational autoencoder” (MVAE), whose prior and posterior distributions are defined over a set of random vectors. We demonstrate that the model can learn interpretable representations of visual scenes that disentangle objects and their properties.