Stochastic Gradient Descent Captures How Children Learn About Physics
This work provides a computational model for cognitive development in children, offering insights into how intuitive physical understanding emerges.
The study investigated whether children's developmental trajectories in understanding physics can be captured by artificial systems, finding that a neural network trained with stochastic gradient descent replicates these trajectories, supporting the idea of development as stochastic optimization.
As children grow older, they develop an intuitive understanding of the physical processes around them. They move along developmental trajectories, which have been mapped out extensively in previous empirical research. We investigate how children's developmental trajectories compare to the learning trajectories of artificial systems. Specifically, we examine the idea that cognitive development results from some form of stochastic optimization procedure. For this purpose, we train a modern generative neural network model using stochastic gradient descent. We then use methods from the developmental psychology literature to probe the physical understanding of this model at different degrees of optimization. We find that the model's learning trajectory captures the developmental trajectories of children, thereby providing support to the idea of development as stochastic optimization.