Teaching a Computer to ‘See’ Galaxies in Hubble Pics

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.

Hubble Photo Body

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.

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.

About Brad Nemire

Brad Nemire
Brad Nemire is on the Developer Marketing team and loves reading about all of the fascinating research being done by developers using NVIDIA GPUs. Reach out to Brad on Twitter @BradNemire and let him know how you’re using GPUs to accelerate your research. Brad graduated from San Diego State University and currently resides in San Jose, CA. Follow @BradNemire on Twitter