In this episode, I'm joined by Adji Bousso Dieng, PhD Student in the Department of Statistics at Columbia University to discuss two of her recent papers, \u201cNoisin: Unbiased Regularization for Recurrent Neural Networks\u201d and \u201cTopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency.\u201d We dive into the details behind both of these papers and learn a ton along the way.