Anoop Deoras is an applied researcher at Netflix where he leads various deep learning projects spanning several products from recommendations to search to home page construction to machine translation for localization. Before joining Netflix, he was working with Microsoft working on Cortana, a virtual personal assistant, innovating and applying advances in spoken language understanding technologies. He did his Ph.D. from Johns Hopkins University where he demonstrated the first ever integration of recurrent neural networks in large vocabulary speech recognition decoders. Anoop is an elect IEEE senior member.
Upcoming Abstract Summary
Building an Incrementally Trained, Local Taste Aware, Global Deep Learned Recommender System Model
In the latter half of the talk, we will discuss how we do incremental learning of deep learned recommender system models. Why do we need to do that ? Everything changes with time. Users’ tastes change with time. What’s available on Netflix and what’s popular also change over time. Therefore, updating or improving recommendation systems over time is necessary to bring more joy to users. In addition to how we apply incremental learning, we will discuss some of the challenges we face involving large-scale data preparation, infrastructure setup for incremental model training as well as pipeline scheduling. The incremental training enables us to serve fresher models trained on fresher and larger amounts of data. This helps our recommender system to nicely and quickly adapt to catalog and users’ taste changes, and improve overall performance.