Enlarge Page:

Become a Member. Learn How >

May 9: How Netflix Predicts My Movie Choices: Recommender Systems and Human Behavioral Modeling

Professor Julian McAuley

Recommender systems such as Netflix use large volumes of data to make personalized predictions that adapt to the needs, nuances, and preferences of individuals. The models may use complex data such as Facebook entries to predict simple responses: whether the individual will like, click on, or purchase an item. How do we get recommendations that are more complex? For example, rather than predicting whether a user will purchase an existing product, can we predict the characteristics or attributes of products that the user will prefer? This presentation will discuss possible extensions to personalized, predictive models of human behavior that will be capable of making such complex recommendations.

Presenter: Julian McAuley is Assistant Professor in the Department of Computer Science and Engineering at UCSD. Previously he was a postdoctoral scholar at Stanford University after receiving his PhD from the Australian National University. His research is concerned with developing predictive models of human behavior using large volumes of online activity data.

May 23: Interactive Machine Learning

Professor Sanjoy Dasgupta

As computers play a larger role in our lives and our work, it is vital for us to be able to interact effectively with them. We need methods for communicating our needs, our preferences, and our knowledge to these machines, and we need mechanisms by which they can explain their inferences to us. This lecture discusses some of the challenges in trying to bridge the communication gap between humans and machines that stems from their very different internal representations.

Presenter: Sanjoy Dasgupta is Professor in the Department of Computer Science and Engineering at UCSD. He received his PhD from Berkeley and spent two years at AT&T Research Labs before joining UCSD. His area of research is algorithmic statistics, with a focus on interactive learning. He is the author of a textbook, Algorithms (with Christos Papadimitriou and Umesh Vazirani), published in 2006.

May 30: Discovering the Brain’s Internal Algorithms: Leveraging Neuroscience to Develop Machine Natural Intelligence

Professor Gabriel Silva

How does the brain represent, learn, and manipulate information differently than existing forms of artificial intelligence? What are the algorithms that achieve this? How does the neurobiology execute such algorithms? And how can we leverage what we learn to engineer forms of natural machine intelligence? As this lecture will explain, our goal is an understanding of the brain’s algorithms in the context of their biological implementation but based on mathematical descriptions independent of the biological details responsible for executing them.

Instructor: Gabriel Silva is Professor and Vice Chair of the Department of Bioengineering and Professor of Neurosciences at UCSD. He is the Founding Director of the Center for Engineered Natural Intelligence and co-director of the Retinal Engineering Center in the Institute of Engineering in Medicine. Silva received his PhD in bioengineering and neurophysiology from the University of Illinois at Chicago.

Coordinator: Jeanne Ferrante

Course Number: OSHR-70060   Credit: 0 units


Email to a friend


Upcoming Sections