Designing Better Sequence Models with RNNs with Adji Bousso Dieng - TWiML Talk #160

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Episode | Podcast

Date: Mon, 02 Jul 2018 17:36:26 -0000

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, “Noisin: Unbiased Regularization for Recurrent Neural Networks” and “TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency.” We dive into the details behind both of these papers and learn a ton along the way.