Machine learning research has yielded many useful algorithms and techniques for solving difficult real-world problems. In this talk, I will discuss how we make practical use of machine learning at Netflix to personalize recommendations for millions of users every day. I will provide a high-level overview of machine learning and discuss the steps involved in applying it to solve real problems. I will then highlight how we use this approach to create a personalized ranking for each user to maximize the user streaming experience. Finally, I will discuss the Cognitive Foundry, an open source software library designed to simplify the use of machine learning algorithms for variety of applications.
Dr. Robert M. Keller will survey the expanding space of music software, motivating the uses of such software and giving particular attention to cases having attributes that could be called “intelligent”. After demonstrating a few examples, he will describe work conducted at Harvey Mudd College on the Intelligent Music Software project, which includes Impro-Visor, an open-source project designed to help jazz musicians improve their improvisation skills. Dr. Keller will include a demonstration of how a computer can learn grammars capable of generating jazz melodies, as well as other nuances.
Ecological processes such as bird migration are complex, difficult to measure, and occur at the scale of continents, making it impossible for humans to grasp their broad-scale patterns by direct observation. However, novel data sources—such as large sensor networks and millions of bird observations reported by human “citizen scientists”—are providing new opportunities to understand ecological phenomena at very large scales. The ability to fit models, test hypotheses, make predictions, and reason about human impacts on biological processes at this scale promise to revolutionize ecological science and environmental policy.
In this talk, I will present novel algorithmic approaches to overcome challenges throughout the “pipeline” from low-level data interpretation to model fitting to high-level decision-making in large-scale ecological science, including: (1) biological interpretation of NEXRAD weather radar, (2) probabilistic modeling of bird migration using citizen science data and (3) optimizing land purchases to support the recovery of endangered species. I will highlight contributions from this work that extend well beyond ecology, including a very general optimization framework for maximizing the spread of a cascading process in a network, and a formalism called Collective Graphical Models for efficiently reasoning about probabilistic models of large populations of individuals when only aggregate data is available.
This colloquium is currently scheduled as a faculty candidate talk.
CGU professor Gondy Leroy will be speaking at Pomona College.
Spring vacation begins after the last class. Classes resume on March 19.
Spring vacation ends at 8:00 a.m. Classes resume today.
This colloquium is currently scheduled as a faculty candidate talk.
To be determined.
In observance of César Chávez Day, no classes are scheduled today. Administrative offices are closed as well.