Talk Title: Deep Learning in Real-Time: Pneumonia Detection. 

Today, the benefit of ML is often conditioned to its deployment in real-time. In this talk, Anita Clement, Data Scientist at Dataiku, will explain how to design and deploy a real-time pneumonia detection engine on Dataiku DSS to power an application that could look like tomorrow’s automated diagnosis tools. Along the cycle of developing such a project, she will highlight key answers to common questions that usually arise when getting started with an image classification project: Tensorflow vs PyTorch [Lightning] CNN: how to choose an architecture Transfer learning or training from scratch Deploying a deep learning model to an API service