6:00-6:30 - Doors Open + Pizza
6:30-7:15 - Michal's Talk
7:15-8:00 - Megan's Talk
8:00 - Q&A
Abstract: The focus of this talk is to provide an introduction to Natural Language Processing. We will use a Word2Vec model to convert the movie synopses to a numeric vector known as word embeddings. From there, we can build a supervised learning model that will predict the movie genre based on these word embeddings. The talk will cover the theory behind Word2Vec as well as tips and tricks for building supervised learning models. We will use H2O, an open source, distributed machine learning platform, to implement these models.
Michal Kurka is a software engineer at H2O.ai. He has a background in architecting big data platforms that utilize machine learning. In H2O.ai he works on core & algorithms, he is responsible for H2O's implementation of the word2vec algorithm. He holds a Master of Computer Science from Charles University in Prague. His field of study was Discrete Models and Algorithms with a focus on Optimization.
Megan is a Customer Data Scientist at H2O. Prior to working at H2O, she worked as a Data Scientist building products driven by machine learning for B2B customers. She has experience working with customers across multiple industries, identifying common problems, and designing robust and automated solutions.