【海韵讲座】2025年第17期 Randomized Single-Layer Gaussian Process Neural Networks for Data Science Applications
主讲人： John W. Paisley Associate Professor of Dept of Electrical Engineering and member of Data Sciences Institute at Columbia University
报告时间：2025年06月07日（星期六）10:00-11:00
报告地点：信息学院6号楼 209
报告摘要：
This talk discusses applications of the random Fourier feature construction of the Gaussian process to some fundamental machine learning problems. This includes (1) interpretable classification and regression with neural additive models, (2) collaborative filtering with nonlinear matrix factorization, and (3) density estimation using GP-tilted functions. Foreach of these problems, a single-layer neural network based on the Gaussian process is employed for which the randomized weights remove the need to learn network parameters. As a result, the learning algorithms are drastically simplified while retaining much of the learning power of nonlinear models for the low-dimensional problems considered.
报告人简介：
Prof. John Paisley is an Associate Professor in the Department of Electrical Engineering at Columbia University, where he is also a member of the Data Science Institute. His research interests include Bayesian models and inference, with applications to machine learning problems. Before joining Columbia in 2013, he was a postdoctoral researcher in the computer science departments at Princeton University and UC Berkeley. Hereceived the BSE and PhD degrees in Electrical and Computer Engineering from Duke University in 2004 and 2010, respectively.
邀请人：信息与通信工程系 丁兴号教授
