SUBJECT: &NAME Research Lecture : Speaker : &NAME &NAME : &NAME : &NAME : A Variational Inference Engine for &NAME &NAME &NAME RESEARCH LECTURE SPEAKER : &NAME &NAME INSTITUTION : Interview Talk HOST : &NAME &NAME DATE : Tuesday March &NUM , &NUM TIME : &NUM : &NUM - &NUM : &NUM PLACE : &NAME Theatre , &NAME Research Ltd &NUM &CHAR &CHAR &NAME Avenue ( Off &NAME Road ) &NAME TITLE : &NAME : A Variational Inference Engine for &NAME &NAME In recent years variational methods have become a popular tool for approximate inference and learning in a wide variety of probabilistic models , with applications ranging from bioinformatics to machine vision . For each new application , however , it is currently necessary first to derive the variational update equations , and then to implement them in application-specific code . Each of these steps is both time consuming and error prone . In this talk I will give an introduction to variational inference methods and describe a general purpose inference engine called &NAME ( Variational Inference for BayESian Networks ' ) which allows a wide variety of probabilistic models to be implemented and solved variationally without recourse to coding . The talk will include a demo of &NAME being used with a number of different models . You are currently subscribed to msrclectures as : &EMAIL To unsubscribe send a blank email to &EMAIL