Karim Pichara

I'm currently an Associate Professor at the Computer Science Department from Universidad Católica de Chile and Research Assistant at the Institute of Applied Computational Science (IACS) from Harvard University. I´m also a researcher in the Millenium institute of Astrophysics (MAS). I received a Ph. D. degree in Computer Science from Universidad Católica in Chile, 2010. During 2011-2012, I did a postdoc in Machine Learning for Astronomy, at Harvard University. My main research areas are Data Science and Machine Learning for Astronomy, focusing in the development of several new tools for automatic classification of variable stars, detection of quasars, discovery of known objects, dealing with missing data, and meta classification, among others.

Research Interest: Data Mining, Machine Learning, Astro-Statistics and Astro-Informatics
kpb@ing.puc.cl - kpichara@seas.harvard.edu

Data Mining

In this course we study and implement most of the basic algorithms in Data Mining, such as association rules: Apriori and FP-Growth; linear regression: Gaussian and Polynomial basis functions; automatic classification: loggistic regression, decision trees, Random Forest and Nearest Neighbours; and Clustering: K-Means, DB-Scan, Gaussian Mixtures (with EM) and Hierarchical. We also study techniques for data discretization, integration, transformation and cleaning.


Approximate Bayesian Inference

This course is focusing in the Bayesian approach for Machine Learning. We mainly study approximate inference methods, such as Monte Carlo and variational inference. This course is very practical, we implement most of the techniques we study, mainly with Python.


Probabilistic Graphical Models

In this course we deeply study the theory behind Graphical Models, specifically Bayesian and Markov networks. After the understanding of the theory behind these models, we learn the main algorithms to perform exact inference, structure and parameter learning.


Advanced Python Programming

In this course we study (and mainly implement) advanced topics in Computer Programming such as: Object Oriented design, data structures, functional programming, threading, simulation, meta programming, Input/Output, unit testing and graphical interfaces. We are about finishing a book that will be available online with all the contents of this course.


Publications

Plenary talk at ACAT 2016

I was invited to give a plenary talk in the 17th INTERNATIONAL WORKSHOP ON ADVANCED COMPUTING AND ANALYSIS TECHNIQUES IN PHYSICS RESEARCH (ACAT), more information here: https://indico.cern.ch/event/397113/timetable/#20160121.detailed

Harvard-Chile students exchange program started

During January 2016, several students and professors from Harvard came to Chile to work with students and professors from Pontificia Universidad Católica and University of Chile. This program mainly involves the collaborative work in problems related to data science for astronomy. The program will continue at Harvard during July 2016.

Presentation at the Semantic Web Seminar

Invited to give a talk in the Semantic Web Seminar ( http://ciws.cl )

Research

Our research is focused on Machine Learning and Statistics, mainly applied to the analysis of Astronomical data. I am working in collaboration with professor Pavlos Protopapas from the Institute of Applied Computational Science at Harvard University (http://iacs.seas.harvard.edu/). Our main interest is to develop automatic tools to classify objects in the Universe, based on information provided by telescopes. There are several important challenges to overcome, such as huge data processing algorithms, parallel programming, intelligent integration of expert models, missing data analysis, unsupervised representation, among others. Chile is one of the most attractive places to perform scientist research in Astronomy, given that most of the state of the art telescopes are installed in the North of the Country.

Projects

Automatic Classification of Variable Stars integrating multiple Catalogs

In the last few years, there has been an increased interest towards computer applications for astronomical research. This interest has been mainly triggered by the ongoing and future observational projects expected to deliver huge amounts of high-quality data, which needs to be promptly analyzed. Some illustrative examples are: the upcoming Large Synoptic SurveyTelescope (LSST), the ongoing Vista Variables in the Via Láctea (VVV) ESO Public Survey, and the Atacama Large Millime-ter/submillimeter Array (ALMA), among others...

Postdoc Students

Christian P.

PhD Students

Felipe Rojas Aracena

Ignacio Becker

Master Students

Augusto Sandoval

Claudio Rojas

Patricio Benavente

Ivania Donoso

Lucas Valenzuela

Orlando Vásquez

Javier Machin Matos

Belén Saldías

Hola soy Belén!

Lukas Zorich

Nebil Kawas

Alumni

Daniela Carrasco

Nicolás De La Maza

Nicolás Castro

Andrés Riveros

Isadora Nun

Cristóbal Mackenzie

Tomás Yany

Cristóbal Berger