Congratulations to four of my students who just finished their M.Sc. and B.Sc discussing ML theses!!

Antonio Carta studied how to use deep learning to help CERN physicists filtering out fake trajectory hints in high energy physics (in co-supervision with Felice Pantaleo).

Francesco Crecchi proposed the DropIn technique to make recurrent neural network resilient to missing input data at inference time.

Andrea Cossu extended Echo State Networks and the ReCoPy Python framework with unsupervised anomaly detection mechanisms for sequential data.

Finally, Maurizio Idini presented his work supervised by Paolo Cignoni and Marco Di Benedetto (Visual Computing Lab @ISTI-CNR) regarding range maps denoising by deep learning techniques.

Ad maiora!