Presentation #102.289 in the session Poster Session.
We have recently developed ExoMiner, a new deep neural network, that was used to validate hundreds of new exoplanets. ExoMiner utilizes the unique elements of Kepler SOC/TESS SPOC data validation summary report in their original format in order to classify transit signals. This is unlike the existing machine classifiers that either do not use a comprehensive list of diagnostic tests required for the correct classification or use simplified version of these tests in the form of a few scalar values. In this talk, we will present ExoMiner, its unique characteristic, and what makes it highly accurate. We will also discuss different experiments we have designed to show that ExoMiner is highly reliable for the classification of transit signals and the validation of new exoplanets.