A one-armed CNN for exoplanet detection from light curves
share
We propose Genesis, a one-armed simplified Convolutional Neural Network (CNN)for exoplanet detection, and compare it to the more complex, two-armed CNN called Astronet. Furthermore, we examine how Monte Carlo cross-validation affects the estimation of the exoplanet detection performance. Finally, we increase the input resolution twofold to assess its effect on performance. The experiments reveal that (i)the reduced complexity of Genesis, i.e., a more than 95 of about 0.5 a more realistic performance estimate that is almost 0.7 estimate, and (iii) the twofold increase in input resolution decreases the average performance by about 0.5 exploration of shallower CNN architectures may be beneficial in order to improve the generalizability of CNN-based exoplanet detection across surveys.
READ FULL TEXT