Computer Science Software Engineer
Resume:
MELISSA K. CARROLL
***@**.*********.***
http://www.cs.princeton.edu/~mkc/
EDUCATION
Doctor of Philosophy in Computer Science and Neuroscience, Princeton University, Princeton, NJ Apr. 2011
Dissertation: fMRI Mind Readers : Sparsity, Spatial Structure, and Reliability
Master of Arts in Computer Science, Princeton University, Princeton, NJ Sep. 2006
Master of Science in Computer Science, Pace University, White Plains, NY Jan. 2003
Thesis: A Comparison of Various Genetic and Non-Genetic Algorithms for Aiding the Design of an Artificial Neural Network
that Learns the Wisconsin Card Sorting Test Task
Bachelor of Arts in Psychology, State University of New York at Binghamton, Binghamton, NY May 1999
WORK EXPERIENCE
Software Engineer, Google, New York, NY 2011 Pres.
Develop and implement algorithms in C++ for all aspects of natural language question answering,
including candidate generation, evidence scoring, model learning, evaluation, and production
Mentored an incoming software engineer and an undergraduate engineering intern
Patents pending: Using an Entity Database to Answer Entity-Triggering Questions; Identifying Entity-
Triggering Queries and Description-Triggering Queries
Post-Doctoral Researcher, IBM T.J. Watson Research Center, Yorktown Heights, NY 2010 2011
Conducted research in Machine Learning with emphasis on Business Analytics applications
Employed parallel computing paradigms to scale temporal causal modeling algorithms for handling large datasets
Research Intern, IBM T.J. Watson Research Center, Yorktown Heights, NY (Advisors: G. Cecchi, I. Rish) 2007 2010
Improved the reliability of predictive Functional Magnetic Resonance Imaging (fMRI) models using regularized sparse
regression (Elastic Net)
Designed and implemented parallel regression (LARS-EN) code in C/MPI for the IBM Blue Gene/L supercomputer
Patents pending: Method and System for Discovering Predictive Patterns in High-Dimensonal Data using Sparse
Supervised Component Analysis; Method and System for Predictive Modeling of Brain Activity from fMRI data Using
Dynamic Lasso
Graduate Researcher, Princeton University, Princeton, NJ (Advisors: R. Schapire, K. Norman) 2004 2010
Developed Machine Learning and Signal Processing-based methods for predicting mental states from fMRI data
Implemented AdaBoost in Matlab/C and applied to processing datasets with large feature sets
Completed substantive course research projects in Computer Vision, Bayesian Graphical Modeling, and Genomics
Research Data Manager/Analyst, Weill Medical College of Cornell University, White Plains, NY 1999 2004
Managed data for 20 psychiatric studies (5 lead); designed, developed, and maintained SQL research databases
Developed quality control procedures; provided data management consultation to outside research group
Delivered presentation on issues in clinical data management to study investigators and clinicians
Formulated data analysis strategies, implemented statistical procedures in SAS and SPSS, prepared results for publication
Recruited, trained, and supervised 9 data clerks and 3 junior data manager/analysts
TEACHING EXPERIENCE
Assistant in Instruction, Princeton University, Princeton, NJ
COS 109, Computers in Our World (Instructor: B. Kernighan): held office hours, performed grading Fall 2009
COS 126, General Computer Science (Instructors: D. Clark, K. Wayne): taught twice-weekly precept to 30 Spring 2006
students, presented review session, held office hours, graded, developed test material
COS 402, Artificial Intelligence (Instructor: R. Schapire): held office hours, graded, presented material Fall 2005
Mentor, Princeton Summer Programming Experience, Princeton, NJ 2005, 2006
Advised two undergraduate students on designing and implementing a MySQL database with Perl/DBI front-end
Teaching Transcript Program, Princeton McGraw Center for Teaching and Learning, Princeton, NJ 2005 2011
August 2012 Page 1 of 2
MELISSA K. CARROLL
***@**.*********.***
http://www.cs.princeton.edu/~mkc/
HONORS AND AWARDS
2009
Wu Prize for Excellence, Princeton Engineering (awarded to select final year graduate students)
Princeton Program in Integrative Information, Computer and Application Sciences (PICASso) Fellowship 2006 2008
Organization for Human Brain Mapping (OHBM) Student Travel Award (merit-based) 2006
National Science Foundation Graduate Fellowship Honorable Mention 2005
Pace University Computer Science Distinguished Achievement Award for Academic Excellence 2003
PROFESSIONAL SERVICE
@Google-NY Team: organize visits and talks by prominent authors, musicians, and other guests 2012 Pres.
Google Anita Borg Scholarship Program: Reviewer 2012
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD): Web Chair 2010 2011
Neural Information Processing Systems Conference (NIPS): Reviewer 2010
IEEE Transactions on Signal Processing: Reviewer 2010
NIPS Workshop on Statistical Learning for fMRI (international workshop): Co-Organizer 2008
2007
Princeton PICASso Colloquium for Women in Computational Science (local workshop): Organizer
Princeton Women in Science and Engineering Conference (regional conference): Co-Organizer
2006
Northeast Student Colloquium on Artificial Intelligence (NESCAI): Reviewer
2007, 2008
Princeton Computer Science Graduate Committee: Representative; liaised with faculty, organized events
2004 2010
Princeton Graduate Engineering Ambassadors: Secretary; authored FAQ for prospective students
2005 2007
Princeton Graduate Engineering Council: Computer Science Representative
2005 2006
COMPUTING SKILLS
Matlab, C/C++, MPI, Java, R, Python, Perl, SQL, VBA, SAS, SPSS
PUBLICATIONS
MK Carroll, GA Cecchi, I Rish, R Garg, AR Rao. (2009). Prediction and Interpretation of Distributed Neural Activity
with Sparse Models. Neuroimage, 44(1): 112-122.
MK Carroll, S Cha. (2003). Application of Stacked Generalization to a Protein Localization Prediction Task.
Proceedings, Atlantic Symposium on Computational Biology and Genome Informatics, 7th Joint Conference on
Information Sciences (JCIS 2003): 923-926.
MK Carroll. (2003). The Performance of Evolutionary Artificial Neural Networks in Unambiguous and Ambiguous
Learning Situations. Technical Report No. 189, Pace University School of Computer Science and Information Systems
BS Meyers, JA Sirey, M Bruce, M Hamilton, P Raue, SJ Friedman, C Rickey, T Kakuma, MK Carroll, D Kiosses, G
Alexopoulos. (2002). Predictors of Early Recovery from Major Depression Among Persons Admitted to Community-
Based Clinics: An Observational Study. Archives of General Psychiatry, 59(8):729-35.
SELECTED PRESENTATIONS
MK Carroll, GA Cecchi, I Rish, R Garg, AR Rao. (2008). Increasing Robustness of Sparse Regression with the Elastic
Net. Presentation, NIPS 2008 Workshop on New Directions in Statistical Learning for Meaningful and Reproducible
fMRI Analysis.
MK Carroll, M Dudik. (2007). Feature Induction on fMRI Images Using Regularized Logistic Regression. Poster,
Organization for Human Brain Mapping (OHBM).
MK Carroll, M Dudik, RE Schapire, KA Norman. (2006). Feature Induction Using Boosting and Logistic Regression on
fMRI Images. Presentation, NIPS 2006 Workshop on New Directions on Decoding Mental States from fMRI Data.
MK Carroll, KA Norman, JV Haxby, RE Schapire. (2006). Exploiting Spatial Information to Improve fMRI Pattern
Classification. Poster, Organization for Human Brain Mapping (OHBM).
August 2012 Page 2 of 2
Contact this candidate