Exploring the role of embeddings in Deep Learning

Abstract:
Embeddings are everywhere in machine learning yet usually not very visible. We use embedding layers when one hot encodings don’t cut it or to visualize relations between words but usually we don't appreciate the crucial role they play in artificial intelligence.
This talk tells the story of embeddings by showing not only how they are used in different deep learning models, but also how they can really help us get an intuition about how these models function.
We'll start by looking at MNIST handwritten digits, before moving on to embedding words for fun and profit. After that we'll look at modern image recognition systems and how that recognition is just a nearest neighbor search on the produced embeddings.
We'll close by looking at how embeddings are used in machine translation and how that work opens up the tantalizing perspectives of using thought vectors towards general intelligence.

Bio:
Douwe Osinga is a serial entrepreneur and a machine learning enthusiast, currently working at Sidewalk Labs as the Tech Lead on Generative Urban Design. Before coming to New York he founded Triposo in Berlin, Germany, everybody's favorite mobile travel guide. Before that he worked for Google in Switzerland, India and Australia. He's the author of "Deep Learning Cookbook.