From dbush1 at stanford.edu Wed May 2 13:24:14 2018
From: dbush1 at stanford.edu (Diane Bush)
Date: Wed, 2 May 2018 20:24:14 +0000
Subject: [Mobilizeplans-starstudents] May 3rd Mobilize Center Seminar,
Abubakar Abid
Message-ID: <0321D0E1-BD6E-4960-9CD5-FA19F1848F96@stanford.edu>
The next Mobilize Center Seminar is scheduled for TOMORROW Thursday, May 3rd, and features Abubakar Abid, Biomedical Data Science Department, Stanford University. He will be presenting ?Contrastive PCA: A Method for Exploring Patterns Enriched in a Dataset?.
The Mobilize Center seminars are held once a month. Please check Mobilize Events for updates.
We look forward to seeing tomorrow!
TITLE:
Contrastive PCA: A Method for Exploring Patterns Enriched in a Dataset
WHEN:
Thursday, May 3rd
noon - 1 pm
WHERE:
Y2E2 300, Stanford University
Abstract:
Visualization and exploration of high-dimensional data is a ubiquitous challenge across disciplines. Widely used techniques such as principal component analysis (PCA) aim to identify dominant trends in one dataset. However, in many settings we have multiple datasets--- e.g., a treatment and a control experiment--- and we are interested in visualizing and exploring patterns that are specific to one of the datasets. This paper proposes a new method, contrastive principal component analysis (cPCA), which identifies low-dimensional structures that are enriched in a dataset relative to comparison data. In a wide variety of experiments, we demonstrate that cPCA with a background dataset enables us to visualize dataset-specific patterns that are not captured by PCA and other standard methods. We further provide a geometric interpretation of cPCA and provide strong mathematical guarantees for the method. An efficient implementation of cPCA is publicly available, and can be used for exploratory data analysis in many applications where PCA is currently used.
Bio:
Abubakar Abid is a 2nd year PhD student who develops machine learning methods, particularly those with applications to medicine and biology. He is advised by Professor James Zou, from the Biomedical Data Science department at Stanford. Abubakar is a 2016 Paul and Daisy Soros Fellow and a recipient of the Stanford Graduate Fellowship.Abubakar Abid is a 2nd year PhD student who develops machine learning methods, particularly those with applications to medicine and biology. He is advised by Professor James Zou, from the Biomedical Data Science department at Stanford. Abubakar is a 2016 Paul and Daisy Soros Fellow and a recipient of the Stanford Graduate Fellowship.
To keep up-to-date on upcoming speakers and the dates, visit Mobilize Events.
Diane Bush
Assistant to Professor Scott Delp
NMBL, Mobilize Center, OpenSim
Stanford University
dbush1 at stanford.edu
.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.
nmbl_core_members mailing list
nmbl_core_members at lists.stanford.edu
https://mailman.stanford.edu/mailman/listinfo/nmbl_core_members
.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.=.
nmbl_core_members mailing list
nmbl_core_members at lists.stanford.edu
https://mailman.stanford.edu/mailman/listinfo/nmbl_core_members
-------------- next part --------------
An HTML attachment was scrubbed...
URL: