CMU/Language Technologies Institute:Research

About
   Directions
   Admissions
   How To Apply
   The LTI Brochure

Education
   Ph.D.
   Dual Ph.D. with Portugal
   M.S.
   Undergrad Minor
   Courses
    FYI

LTI Forms

Seminars
   LTI Seminar Series
   Joint Speech Seminar (JSS)
   Machine Translation (MT)
   Student Research Symposium
   Information Retrieval Series
   Large Scale Lunch Seminar    Intelligence Seminar

Visitor Information
   General
   Maps & Directions
   Hotel Links
   Parking Information

Research
   Projects
   Reports
    Dissertations

People
   Faculty
   Students
   Upcoming Graduates
   Staff
   Visitors
   Who to See for What

Contacts

11-765: Active Learning Seminar

Department: Language Technologies Institute (LTI)
Units: 6
Semester: Fall
Instructor: Jaime Carbonell
Start Date: September 4, 2008
Time: 4:30pm - 6:20pm
Room: Newell Simon Hall 1109
Mailing List: active-learning-seminar@cs.cmu.edu

Course Description:

Active Learning seeks to sample the most instructive instances to obtain labels in order to optimize performance (e.g. minimize the loss function) of different learning algorithms, multiple state-of-the-art methods will be examined including uncertainty sampling, density sampling, diversity sampling, ensemble and multi-strategy methods. We will also discuss extensions such as active learning to rank, proactive learning, and de-novo hidden class discovery.

Presentations:

Date	Presenter(s)	Title
September 11	Sivaraman Balakrishnan and Kriti Puniyani	Combining Active Learning and Semi-supervised Learning Using Gaussian Fields and Harmonic Functions Reading: Improving Generalization with Active Learning
September 18	Henry Shu	Paired-Sampling in Density-Sensitive Active Learning
September 25	Steve Hanneke	A General Agnostic Active Learning Algorithm
October 2	Ramnath Balasubramanyan and Mladen Kolar	Active Learning for Logistic Regression: An Evaluation, Andrew I. Schein and Lyle H. Ungar
October 9	Mehrbod Sharifi and Diwakar Punjani	Strategy Selection in Active Learning
October 16	Vamshi Ambati and Jonathan Clark	Cost Sensitive and Proactive Learning
October 23	Jingrui He	Active Learning in SVMs Readings: Support Vector Machine Active Learning with Applications to Text Classification Incorporating Diversity in Active Learning with Support Vector Machines
October 30	Stephanie Rosenthal	Active Learning with Feedback on Both Features and Instances
November 6	Oznur Tastan	Cost-sensitve Active Feature-value Acquisition
November 13	Tae Yano	Active Learning Driven Data Acquisition for Sensor Networks and coinciding Powerpoint Cost-effective Outbreak Detection in Networks and coinciding Powerpoint
November 20	Xi Chen and Bin Fu	Active Learning for Rare-Category Detection (Powerpoint) Readings: Nearest-Neighbor-Based Active Learning for Rare Category Detection Active Learning for Anomaly and Rare-Category Detection
November 25	Rashmi Gangadharaiah	Active Learning for Statistical Natural Language Parsing MMR-based Active Machine Learning for Bio Named Entity Recognition An Empirical Study of the Behavior of Active Learning for Word Sense Disambiguation Active Learning for Natural Language Processing (Powerpoint)

Reference Materials :

Active Learning Candidate Readings (Updated)

Powerpoint - 4 September, 2008

The LTI Webmaster

LTI is part of the School of Computer Science at Carnegie Mellon University.
This page is maintained by The LTI Webmaster