COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > CCIMI Short course - Graph-based Approaches to Learning: Mathematical Theory and Perspectives
CCIMI Short course - Graph-based Approaches to Learning: Mathematical Theory and Perspectives
Add to your list(s)
Send you e-mail reminders
Further detail
This short course is organised by the CCIMI and open to all. Lectures run 11:00-12:30, Monday 3rd, Wednesday 5th, Friday 7th, Monday 10th and Wednesday 12th June in MR14 . Instructor: Nicolas Garcia Trillos, University of Wisconsin-Madison In this mini course we will explore graph-based approaches to supervised, semi-supervised, and unsupervised learning. We will use graphs as a way to summarize the measure of similarity between observed data points (endowing the data set with a geometric structure in this way), and in particular we will use them to define “priors” or “regularizers” on unknown quantities of interest (be it a classification rule, a clustering of a data set, etc), in direct analogy with PDE or variational models found in the applied analysis literature (like for example in image analysis or geosciences). The proposed outline for the mini-course is as follows: Lecture 1: Introduction. How can geometry help us learn from data? Optimization and Bayesian approaches. Lecture 2: Consistency results. Spectral methods, Calculus of Variations methods, PDE methods. Part 1. Lecture 3: Consistency results. Spectral methods, Calculus of Variations methods, PDE methods. Part 2. Lecture 4: Stability of algorithms in Bayesian computing. Lecture 5: How can we learn geometry from data? If you have a question about this list, please contact: J.W.Stevens; Paula Smith. If you have a question about a specific talk, click on that talk to find its organiser. 0 upcoming talks and 6 talks in the archive. Lecture 6: Impact of choice of metric in learningNicolas Garcia Trillos. Centre for Mathematical Sciences, MR14. Friday 14 June 2019, 11:00-12:30 Lecture 5: Other constructions on graphs (discrete optimal transport)Nicolas Garcia Trillos. Centre for Mathematical Sciences, MR14. Wednesday 12 June 2019, 11:00-12:30 Lecture 4: Consistency results. Spectral methods, Calculus of Variations methods, PDE methods. Part 3Nicolas Garcia Trillos. Centre for Mathematical Sciences, MR14. Monday 10 June 2019, 11:00-12:30 Lecture 3: Consistency results. Spectral methods, Calculus of Variations methods, PDE methods. Part 2Nicolas Garcia Trillos. Centre for Mathematical Sciences, MR14. Friday 07 June 2019, 11:00-12:30 Lecture 2: Consistency results. Spectral methods, Calculus of Variations methods, PDE methods. Part 1Nicolas Garcia Trillos. Centre for Mathematical Sciences, MR14. Wednesday 05 June 2019, 11:00-12:30 Lecture 1: Introduction. How can geometry help us learn from data? Optimization and Bayesian approaches.Nicolas Garcia Trillos. Centre for Mathematical Sciences, MR14. Monday 03 June 2019, 11:30-12:30 Please see above for contact details for this list. |
Other listsKing's Sustainability Series Centre for Smart Infrastructure & Construction Seminars Babbage Lecture SeriesOther talksTerahertz lights up the nanoscale: Paving the way for nanotechnology via terahertz spectroscopy. Talk 1. Awareness in sight: Self and other appraisals of disability in acquired brain injury Talk 2. The regulation of intrusive autobiographical memories Annual General Meeting Reprogramming the genetic code The structure of the proton and the exploration of the high-energy frontier Hong-Ou-Mandel effect under partial time reversal: a destructive interference effect in the amplification of light |