Mohit Prashant

Mohit Prashant

I am an AI researcher with a focus in machine learning safety and risk. My PhD work is in deriving probabilistic guarantees for RL systems and agents using learning theory (PAC framework).

Building Robust Systems Using Adversarial Input Masking

Date:

Presentation at STCAI2021 on using generative adversarial networks to build robust systems using a form of input masking. The results of the study showed that informed masking allowed for better regularization on image prediction than dropout and can be used in conjunction with existing data augmentation methods. Recording attached inside.