Spectral classification using convolutional neural networks
Masaryk University, Department of Theoretical physics and Astrophysics, Faculty of Science
arXiv:1412.8341 [cs.CV], (29 Dec 2014)
There is a great need for accurate and autonomous spectral classification methods in astrophysics. This thesis is about training a convolutional neural network (ConvNet) to recognize an object class (quasar, star or galaxy) from one-dimension spectra only. Author developed several scripts and C programs for datasets preparation, preprocessing and post-processing of the data. EBLearn library (developed by Pierre Sermanet and Yann LeCun) was used to create ConvNets. Application on dataset of more than 60000 spectra yielded success rate of nearly 95%. This thesis conclusively proved great potential of convolutional neural networks and deep learning methods in astrophysics.
December 30, 2014 by hgpu