UK researchers are teaching computers to see and label galaxies using unsupervised machine learning. The group from the University of Hertfordshire, Hatfield, presents a novel unsupervised learning approach to automatically segment and label images in astronomical surveys.
Automation of this procedure will be essential as next-generation surveys enter the petabyte scale: data volumes will exceed the capability of even large crowd-sourced analyses. We demonstrate how a growing neural gas (GNG) can be used to encode the feature space of imaging data. When coupled with a technique called hierarchical clustering, imaging data can be automatically segmented and labelled by organizing nodes in the GNG. The key distinction of unsupervised learning is that these labels need not be known prior to training, rather they are determined by the algorithm itself. Importantly, after training a network can be be presented with images it has never ‘seen’ before and provide consistent categorization of features.
Teaching a Computer to ‘See’ Galaxies in Hubble Pics
Jul 15, 2015
Discuss (0)

AI-Generated Summary
- Researchers from the University of Hertfordshire are using unsupervised machine learning to teach computers to identify and label galaxies in astronomical surveys.
- The team uses a growing neural gas (GNG) combined with hierarchical clustering to automatically segment and label images without prior knowledge of the labels.
- This automation is crucial for next-generation surveys that will produce petabyte-scale data, exceeding the capacity of large crowd-sourced analyses.
AI-generated content may summarize information incompletely. Verify important information. Learn more
The research team used a Tesla K40 and is working now to port parts of their code to CUDA in hopes to dramatically improve their performance.