Michael Manapat talks about how to choose, train, and evaluate models, how to bridge the gap between training and production systems, and avoiding pitfalls.
Kristjan Korjus discusses deep learning, reinforcement learning and their combination called deep Q-Network.
Ali Kheyrollahi uses clustering and network analysis algorithms to analyze the publicly available Wiki data on rock music to find mathematical relationship between artists, trends and subgenres.
Alena Hall presents various machine learning algorithms available in Accord.NET - a framework for machine learning and scientific computing in .NET.
Brian Wilt discusses how applied machine learning techniques and data science helped Jawbone build a successful fitness tracking app.
Lucian Vlad Lita focuses on the next step in personalization: well-designed software architectures for storing, computing, and delivering responsive, accurate in-product predictions and experiments.
Leah McGuire describes the machine learning platform Salesforce wrote on top of Spark to modularize data cleaning and feature engineering.
Ajit Jaokar discusses data science and IoT: sensor data, real-time processing, cognitive computing, integration of IoT analytics with hardware, IoT’s impact on healthcare, automotive, wearables, etc.
Mini-talks: The Machine Intelligence Landscape: A Venture Capital Perspective. The future of global, trustless transactions on the largest graph: blockchain. Algorithms for Anti-Money Laundering
Soumith Chintala introduces deep learning, what it is, why it has become popular, and how it can be fitted into existing machine learning solutions.
Peter Harrington explains what you do with machine learning, and what are the building blocks for an application that uses machine learning from collected data to creating predictions for customers.
Peter Norvig keynotes on using machine learning techniques to solve more general software problems, helping both the advanced programmer and the novice one.