BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Sparse Bayesian nonparametric models for genomic d
 ata analysis
DTSTART:20130318T161500
DTEND:20130318T173000
DTSTAMP:20260406T194612Z
UID:53d796519ceb7e1aeefcedd13a97bcc0cd1f2f8c0c8478d98bfdb731
CATEGORIES:Conferences - Seminars
DESCRIPTION:David Knowles\, Stanford University\nIC faculty candidate\nAbs
 tract\nMotivated by the desire to understand gene regulatory networks we d
 evelop two Bayesian nonparametric models which find modules of co-regulate
 d genes from transcriptomic data. The first\, Dirichlet Process Variable C
 lustering (DPVC)\, partitions genes into disjoint clusters\, whereas the s
 econd\, Nonparametric Sparse Factor Analysis (NSFA)\, allows genes to belo
 ng to an arbitrary number of modules. The superior predictive performance 
 of the later model suggests that multiple membership more closely resemble
 s the true nature of gene regulatory networks. We extend DPVC to allow sim
 ilar but different modules in different data views\, such as cell types\, 
 and extend NSFA to a multitask regression setting where our aim is to pred
 ict the sensitivity of cancer cell lines to therapeutic compounds using ge
 netic and molecular characteristics. While we use genomic data analysis pr
 oblems to motivate these models\, they have much wider applicability and c
 orrespond to canonical analyses such as variable clustering\, dimensionali
 ty reduction\, and multitask learning.Biography\nI am a post-doctoral rese
 archer with Daphne Koller in the Computer Science Department at Stanford U
 niversity. I did my PhD with Zoubin Ghahramani in the Machine Learning gro
 up of the Cambridge University Engineering Department\, during which I wor
 ked part-time at Microsoft Research Cambridge developing Infer.NET\, a pro
 babilistic inference framework. Prior to my PhD I obtained a masters in Bi
 oinformatics and Systems Biology from Imperial College London. My undergra
 duate degree at the University of Cambridge comprised two years of Physics
  before switching to Engineering to complete an MEng with Professor Ghahra
 mani.  My research involves both the development of novel machine learnin
 g methods and their application to challenging data analysis problems in b
 iology.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR