avatar
AstroAI
Developing Artificial Intelligence to Solve the Mysteries of the Universe
  • HOME
  • RESEARCH
  • EARTHAI
  • PEOPLE
  • EVENTS
  • LATEST NEWS
  • LUNCH TALKS
  • SUMMER PROGRAM
  • WORKSHOP
  • APPLY
  • CONTACT
Home AstroAI Workshop 2025
Workshop_abstract
Cancel

AstroAI Workshop 2025

Details Invited Speakers Abstracts Register Schedule Venue Accommodations Code of Conduct

Core Park

Exploring Compositional Generalization of Neural Networks through Synthetic Experiments

Presenter: Core Park (Harvard University)

Title: Exploring Compositional Generalization of Neural Networks through Synthetic Experiments

Date/Time: Thursday, July 10th, 3:00 - 5:00 PM

Abstract: Interpreting neural networks remains a significant challenge due to their complexity. Approaches range from fine-grained mechanistic analyses to evaluating broad performance benchmarks. This tutorial introduces an intermediate strategy: understanding neural network behavior via controlled synthetic experiments. Using a synthetic toy model of spectral detection—where spectral abundances map directly to generated spectra—we will train neural networks to infer abundances from spectra alone. By systematically varying training data distributions, we will analyze when neural networks compositionally generalize to scenarios unseen during training. We will replicate and extend prior observations from generative diffusion models, mainly investigating generalization across multiple dimensions. Participants are encouraged to explore and test various hypotheses within this controlled experimental framework in an open ended way.

Requirements: Installed jupyter notebook or colab with numpy, matplotlib, pytorch.

-->

© 2025 AstroAI. Some rights reserved.

Powered by Jekyll with Chirpy theme.

A new version of content is available.