Scott Clark introduces Bayesian Global Optimization as an efficient way to optimize ML model parameters, explaining the underlying techniques and comparing it to other standard methods.
Steven Cooper discusses using machine learning to understand malformed API requests to not only respond with a best fit response, but capture the user errors for future responses.
Rob Harrop discusses the increasing automated field of operations and what the future might hold when machine learning and AI techniques are brought to bear on the problem of systems operations.
Nikhil Garg talks about the various Machine Learning problems that are important for Quora to solve in order to keep the quality high at such a massive scale.
Clarence Chio talks about the creation of a real-world relevance and recommendation system from scratch.
Lawrence Spracklen creates a machine learning model leveraging data within MPP databases such as Apache HAWQ or Greenplum integrated with Chorus and then deploying this as a microservice on PCF.
Rajat Monga talks about why Google built TensorFlow, an open source software library for numerical computation using data flow graphs, and what were some of the technical challenges in building it.
The panelists discuss the impact machine learning is having on various industries.
Hollin Wilkins discusses the reasons behind MLeap, outes the programming time saved by using it, shows benchmarks of several online models, and provides a demo and examples of using it in practice.
James Weaver takes a deeper dive into machine learning topics such as supervised learning, unsupervised learning, and deep learning, surveying various machine learning APIs and platforms.
Alok Aggarwal overviews Artificial Intelligence and discusses a use case, “Voice of Cancer Patients” that uses ML and NLP algorithms to analyze unstructured text written by cancer patients.
Danny Lange presents Uber’s Machine Learning service that can perform functions such as ETA, fraud detection, churn prediction, forecasting demand, and much more.