Stochastic Gradient Descent Captures How Children Learn About Physics
Luca M. Schulze Buschoff, Eric Schulz, Marcel Binz

TL;DR
This paper explores how stochastic gradient descent in neural networks can model children's physical learning processes, showing that artificial learning trajectories mirror human developmental stages.
Contribution
It demonstrates that neural networks trained with stochastic gradient descent can replicate children's developmental trajectories in understanding physics.
Findings
Model's learning trajectory aligns with children's developmental stages
Supports the hypothesis that cognitive development can be viewed as stochastic optimization
Provides a computational perspective on developmental psychology
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputational Physics and Python Applications
