A one-armed CNN for exoplanet detection from light curves

by   Koko Visser, et al.

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.



page 1

page 5


Classifying Multi-Gas Spectrums using Monte Carlo KNN and Multi-Resolution CNN

A Monte Carlo k-nearest neighbours (KNN) and a multi-resolution convolut...

CNN Based Posture-Free Hand Detection

Although many studies suggest high performance hand detection methods, t...

Experimental Exploration of Compact Convolutional Neural Network Architectures for Non-temporal Real-time Fire Detection

In this work we explore different Convolutional Neural Network (CNN) arc...

Feeding Hand-Crafted Features for Enhancing the Performance of Convolutional Neural Networks

Since the convolutional neural network (CNN) is be- lieved to find right...

Solar Cell Surface Defect Inspection Based on Multispectral Convolutional Neural Network

Similar and indeterminate defect detection of solar cell surface with he...

Seizure Detection and Prediction by Parallel Memristive Convolutional Neural Networks

During the past two decades, epileptic seizure detection and prediction ...

Prediction of progressive lens performance from neural network simulations

Purpose: The purpose of this study is to present a framework to predict ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.