Waleed Abdulla: How Convolutional Networks Work and What they See

Abstract
Convolutional Neural Networks (CNNs) have been very successful in computer vision applications. In this presentation I'll explain how CNNs do what they do, what they excel at, and where they might fail. There will be examples and visualizations of how an input image is transformed as it goes through the layers of a neural network. And I'll discuss common methods used to peek inside CNNs to understand their inner workings or debug them. While there will be some code examples, the presentation is not overly technical, and should be useful to beginners as well as deep learning practitioners.

Agenda:
• 18.00: Doors Open
• 18.15: Main Presentation
• 19:00: Q/A
• 19:15: Mingling

Speaker
Waleed Abdulla is a deep learning engineer focusing on computer vision applications. He writes about deep learning and builds open source projects. His most recent project, Mask RCNN, is one of the top instance segmentation tools, used by thousands of deep learning developers. He's an independent consultant, while also working on his next startup project. Before getting into deep learning, he built a startup in the news and social media space, raised VC funding, and was in 500Startups and the Facebook fbFund before that. He also served on the board of Hacker Dojo, a non-profit co-working space. And he's often active in organizing technology events, meetups, and hackathons.