The Acquisition of Physical Knowledge in Generative Neural Networks
Luca M. Schulze Buschoff,u00a0Eric Schulz,u00a0Marcel Binz
As children grow older, they develop an intuitive understanding of the physical processes around them. Their physical understanding develops in stages, moving along developmental trajectories which have been mapped out extensively in previous empirical research. Here, we investigate how the learning trajectories of deep generative neural networks compare to childrenu2019s developmental trajectories using physical understanding as a testbed. We outline an approach that allows us to examine two distinct hypotheses of human development u2013 stochastic optimization and complexity increase. We find that while our models are able to accurately predict a number of physical processes, their learning trajectories under both hypotheses do not follow the developmental trajectories of children.
