Neural nets at the edge being Gaussians.
Instilling Inductive biases
HYPERNETWORKS (MAML and networks producing networks)
Neuronal weight and layer interpretability( new paper i heard abt used an auto encoder or smt to figure out which neurons were responsible for certain changes in behavior, seemed interesting, could be interesting for understanding how to instill information directly into a network)
Im in the exact same sort of position. Anomaly detection built in java backend, data discovery and extraction with sql and sqoop, spark/Hadoop data preprocessing, ml model training in cloud and a rest API for it all alone