Exploring Convolutional Neural Networks for Gravitational Wave data analysis

Gravitational wave astronomy can benefit from the rapid classification of gravitational wave signals buried deep in instrumentation noise. In 2017, George and Heurata (and since then other researchers) have considered Convolutional Neural Networks to detect gravitational waves signals and estimate some of the corresponding binary's parameters (i.e. distance, total mass, mass ratio and orientation in the sky). In this talk I will summarize efforts to extend this classification and prediction strategy. In particular, we discuss strategies to optimize the hyper parameters of our network, in an attempt to make our networks as compact and effective as possible. Preliminary results will be discussed for some simple setups.