Productionizing Deep Learning Models
Lessons learned from productionizing deep learning models. How to go about improving existing production models. How to organize the infra and modeling efforts. Automating continuous training. Online vs offline metrics.
Nicholas Leonard is a software engineer at Twitter Cortex. He was a core contributor to Lua Torch and worked to migrate ML infra to TensorFlow. He is currently in the Cortex Applied Machine Learning team, were he works with customer teams like Ads Prediction and Health ML to improve their existing models. He graduated from the Royal Military College of Canada and holds an MS in computer science from the University of Montreal.