This shows you the differences between two versions of the page.
|
cv [2013/08/19 09:55] finale [Professional and Academic Service] |
cv [2013/10/09 15:55] (current) finale |
||
|---|---|---|---|
| Line 7: | Line 7: | ||
| ==== Research Summary ==== | ==== Research Summary ==== | ||
| - | My current projects include understanding the temporal evolution of Autism Spectrum Disorder and evaluating drug efficacy among diabetics using electronic health records (EHRs). While EHRs provide an inexpensive way to look at large clinical populations, they are extremely sparse and incomplete. Developing novel Bayesian methodologies to handle these challenges is the core of my current research. Specifically, I am interested in models and inference procedures that can take advantage of input and intutions from experts in a flexible and robust manner. | + | My core research interest lies in developing unsupervised machine learning techniques that have both high predictive and explanatory power. My current projects include understanding the temporal evolution of Autism Spectrum Disorder and evaluating drug efficacy among diabetics using electronic health records (EHRs). While EHRs provide an inexpensive way to look at large clinical populations, they are extremely sparse and incomplete. Specifically, I am interested in models and inference procedures that can take advantage of input and intutions from experts in a flexible and robust manner. |
| More generally, I am interested in a variety of machine learning problems centered around Bayesian modeling and sequential decision-making. My doctoral work focused on applying Bayesian nonparametrics to reinforcement learning problems in partially observable domains. For my first masters, I developed an adaptable dialog manager for a robotic wheelchair using a planning paradigm known as partially observable Markov decision processes. During my second masters, I worked on efficient inference techniques for scaling Bayesian non-parametrics to large, real-world problems. In particular, I developed efficient inference algorithms for a latent feature model known as the Indian Buffet Process, which has applications ranging from detecting software bugs to modeling protein interactions. | More generally, I am interested in a variety of machine learning problems centered around Bayesian modeling and sequential decision-making. My doctoral work focused on applying Bayesian nonparametrics to reinforcement learning problems in partially observable domains. For my first masters, I developed an adaptable dialog manager for a robotic wheelchair using a planning paradigm known as partially observable Markov decision processes. During my second masters, I worked on efficient inference techniques for scaling Bayesian non-parametrics to large, real-world problems. In particular, I developed efficient inference algorithms for a latent feature model known as the Indian Buffet Process, which has applications ranging from detecting software bugs to modeling protein interactions. | ||
| Line 14: | Line 14: | ||
| === Research Experience === | === Research Experience === | ||
| * Research Associate in Bioinformatics, Harvard Medical School Center for Biomedical Informatics, September 2012 - Present. Applying Bayesian techniques to cluster and make predictions from clinical data; projects include predicting seizures among autism patients and characterizing cardiovascular risk among healthy women (continuing projects from BWH). | * Research Associate in Bioinformatics, Harvard Medical School Center for Biomedical Informatics, September 2012 - Present. Applying Bayesian techniques to cluster and make predictions from clinical data; projects include predicting seizures among autism patients and characterizing cardiovascular risk among healthy women (continuing projects from BWH). | ||
| - | * Bioinformatics Analyst, Brigham and Women's Hospital, April 2012 - August 2012. Applying Bayesian techniques to cluster and make predictions from clinical data; projects include predicting seizures among autism patients and characterizing cardiovascular risk among healthy women. Research Fellow, September 2012 - Present. | ||
| * Fellow, Harvard School of Engineering and Applied Sciences, January 2012 - Present. Applying Bayesian nonparametric techniques to reinforcement learning domains and developing novel Bayesian nonparametric models. | * Fellow, Harvard School of Engineering and Applied Sciences, January 2012 - Present. Applying Bayesian nonparametric techniques to reinforcement learning domains and developing novel Bayesian nonparametric models. | ||
| * PhD Thesis: Bayesian Nonparametric Methods for Reinforcement Learning in Partially Observable Domains, MIT Fall 2009-Spring 2012. Bayesian Nonparametric Methods are well-suited to reinforcement learning problems where the size of the world is unknown and new areas may be explored over time. My work involved designing Bayesian nonparametric models suitable for reinforcement learning problems and developing the inference techniques to apply them to interestingly-sized domains. | * PhD Thesis: Bayesian Nonparametric Methods for Reinforcement Learning in Partially Observable Domains, MIT Fall 2009-Spring 2012. Bayesian Nonparametric Methods are well-suited to reinforcement learning problems where the size of the world is unknown and new areas may be explored over time. My work involved designing Bayesian nonparametric models suitable for reinforcement learning problems and developing the inference techniques to apply them to interestingly-sized domains. | ||
| Line 36: | Line 35: | ||
| === Projects Supervised === | === Projects Supervised === | ||
| - | * Project Mentor, Wellesley Winter 2012 - Present. Co-supervised an undergraduate project to predict energies of solvation based on molecular features. | + | * Project Mentor, Winter 2013—Present. Massachusetts Institute of Technology. Supervised two undergraduate students to apply basic machine learning techniques to predict diagnoses in autism spectrum disorders and inflammatory bowel disease. |
| + | * Bachelors Thesis Mentor, Winter 2012—present, Wellesley College. Co-supervised two undergraduate theses to predict energies of solvation based on molecular features. | ||
| + | * Project Mentor, Fall 2012-Spring 2013. Harvard. Supervised a project to classify pot-holes based on smart phone accelerometer data. | ||
| * Project Mentor, HMS Summer 2012. Supervised an undergraduate project looking at pathways with high differential gene expression between autistic individuals and a healthy population. | * Project Mentor, HMS Summer 2012. Supervised an undergraduate project looking at pathways with high differential gene expression between autistic individuals and a healthy population. | ||
| * Project Mentor, MIT Summer 2010. Helped supervised an undergraduate project for localizing wheelchairs using wifi signal strengths. | * Project Mentor, MIT Summer 2010. Helped supervised an undergraduate project for localizing wheelchairs using wifi signal strengths. | ||
| Line 43: | Line 44: | ||
| === Industry === | === Industry === | ||
| + | * Bioinformatics Analyst, Brigham and Women's Hospital, April 2012 - August 2012. Applying Bayesian techniques to cluster and make predictions from clinical data; projects include predicting seizures among autism patients and characterizing cardiovascular risk among healthy women. Research Fellow, September 2012 - Present. | ||
| * Intern, ITA Software, Summer 2007. Applied machine learning techniques for econometric analysis of flight data. | * Intern, ITA Software, Summer 2007. Applied machine learning techniques for econometric analysis of flight data. | ||
| * Lab Assistant, Sentor Technologies Inc., Richmond VA, Summer 2003. Programmed and built control circuitry for a contactless gamma ray detector, built reels for electrospray applications. | * Lab Assistant, Sentor Technologies Inc., Richmond VA, Summer 2003. Programmed and built control circuitry for a contactless gamma ray detector, built reels for electrospray applications. | ||
| Line 88: | Line 90: | ||
| === Seminars and Guest Lectures === | === Seminars and Guest Lectures === | ||
| + | * Invited Speaker, February 2014, Duke University. | ||
| + | * Invited Speaker, December 2013, NIPS Workshop on Causal Reasoning. Tutorial of POMDPs for Causal Reasoning. | ||
| + | * Panelist, October 2013, Health 2.0 Conference. Machine Learning for Medical Data Panel. | ||
| + | * Guest Lecturer, October 2013, Harvard University, CS281: Advanced Machine Learning (advanced graduate course). Prepared and presented a lecture on Monte Carlo techniques. | ||
| + | * Speaker, July 2013, BIGG Fellows Program at Harvard Medical School. Machine Learning for Discovering Phenotypes in Autism Spectrum Disorders. | ||
| * Speaker, May 2013, Northeastern University. Bayesian Nonparametric Methods for Timeseries Analysis. | * Speaker, May 2013, Northeastern University. Bayesian Nonparametric Methods for Timeseries Analysis. | ||
| * Speaker, March 2013. Vecna. Characterizing Temporal Patterns in Autism Spectrum Disorder from Electronic Health Records. | * Speaker, March 2013. Vecna. Characterizing Temporal Patterns in Autism Spectrum Disorder from Electronic Health Records. | ||
| Line 103: | Line 110: | ||
| ==== Community Outreach ==== | ==== Community Outreach ==== | ||
| === Statistical Consulting === | === Statistical Consulting === | ||
| - | * Analyst, Statistics without Borders, Winter 2011. Re-analyzed data from a study examining the effectiveness of a maternal health education program on social and health outcomes for a group in Bangalore, India. | + | * Volunteer Analyst, Statistics without Borders. 2009—present. Projects: Re-analyzed data from a study on the effectiveness of maternal health education on social and health outcomes for CARE in Bangalore, India (Winter 2011). Analyzed influences on choices surrounding the consumption of animal products for the Farm Sanctuary (Fall 2013). |
| - | * Expert consultant for reviewing a report on the Liberian Truth Commission (Bird, Annie. 'A Preliminary Assessment of the Impact of the Liberian Truth and Reconciliation Commission,' An independent evaluation undertaken as part of the Human Rights Data Analysis Group (HRDAG) at Benetech's grant from the United States Department of State Bureau for Democracy, Human Rights and Labor (DRL), January 2010). | + | * Volunteer Analyst, Learning Unlimited, 2011-2012. Organized focus groups to determine what aspects of MIT's Educational Studies Program's events had the most lasting effects on students. |
| + | * Expert reviewer for a report on the Liberian Truth Commission (Bird, Annie. 'A Preliminary Assessment of the Impact of the Liberian Truth and Reconciliation Commission,' An independent evaluation undertaken as part of the Human Rights Data Analysis Group (HRDAG) at Benetech's grant from the United States Department of State Bureau for Democracy, Human Rights and Labor (DRL), January 2010). | ||
| * Statistical consultant for evaluating effectiveness of various diarrhea treatment programs in Africa (Millenium Villages, Winter 2010). | * Statistical consultant for evaluating effectiveness of various diarrhea treatment programs in Africa (Millenium Villages, Winter 2010). | ||