Automatic Design of Artificial Neural Networks for Gamma-Ray Detection

Abstract

The goal of this work is to investigate the possibility of improving current gamma/hadron discrimination based on their shower patterns recorded on the ground. To this end we propose the use of Convolutional Neural Networks (CNNs) for their ability to distinguish patterns based on automatically designed features. In order to promote the creation of CNNs that properly uncover the hidden patterns in the data, and at same time avoid the burden of hand-crafting the topology and learning hyper-parameters we resort to NeuroEvolution; in particular we use Fast-DENSER++, a variant of Deep Evolutionary Network Structured Representation. The results show that the best CNN generated by Fast-DENSER++ improves by a factor of 2 when compared with the results reported by classic statistical approaches. Additionally, we experiment ensembling the 10 best generated CNNs, one from each of the evolutionary runs; the ensemble leads to an improvement by a factor of 2.3. These results show that it is possible to improve the gamma/hadron discrimination based on CNNs that are automatically generated and are trained with instances of the ground impact patterns.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• Genetic Algorithms for Evolving Deep Neural Networks
• DENSER: Deep Evolutionary Network Structured Representation
• Design and expected performance of a novel hybrid detector for very-high-energy gamma astrophysics
• Towards the Evolution of Multi-Layered Neural Networks: A Dynamic Structured Grammatical Evolution Approach
• Evolutionary Neural AutoML for Deep Learning
• Fast-DENSER++: Evolving Fully-Trained Deep Artificial Neural Networks

Cited by in corpus (5)

• A Survey on Evolutionary Neural Architecture Search
• Muon identification in a compact single-layered water Cherenkov detector and gamma/hadron discrimination using Machine Learning techniques
• $P_{\gamma h}^{\alpha }$: a new variable for $\gamma /\mathrm{h}$ discrimination in large gamma-ray ground arrays
• Discriminating sub-TeV gamma and hadron-induced showers through their footprints
• Application of Graph Networks to a wide-field Water-Cherenkov-based Gamma-Ray Observatory