Facundo Bromberg

Facundo Bromberg

Facundo Bromberg is currently a Full Professor and Director of the Artificial Intelligence DHARMa Research Group at the  Universidad Tecnológica Nacional (UTN), and an Adjunct Researcher at the CONICET (Argentinean Research Council). During his career he has mentored several Ph.D. thesis, 5 already graduated and 5 in processes. He is also the director of the Masters Program Inteligencia Digital para la Innovación (Digital intelligence for Innovation). In the past ee has also participated as invited professor in several Ph.D. programs in Argentina, and actively participated in organization of different activities of the AAIA (Argentinean Association of Artificial Intelligence), such as co-organizing the Argentinean Symposium of Artificial Intelligence (ASAI) in 2009, co-organized the 1st and 2nd Argentinean Schools in Artificial Intelligence (EAIA) in 2012 and 2013, and is currently co-organizing the IJCAI International School of AI to be held in Buenos Aires in 2014.

Personal biography

Facundo was born in the City of Mendoza (Argentina) in March of 1974. With only two years his family moved to Israel, where they stayed until the end of 1982, after which they returned to Mendoza. He leaves Mendoza again in 1994 to S. C. de Bariloche to study Physics in the Instituto Balseiro, where he stayed until 1998. From there he moves to Buenos Aires City for two years, coming back to Mendoza with 26 years old, in the year 2000. Back in Mendoza he meets his current wife, Natalia Juan-Miguez, with whom he leaves to the United States in 2001 for his Ph.D. studies. In the year 2006 their daughter Zoe is born in Ames, Iowa, and in 2007 all three leaves back to Mendoza after Facundo finishes his studies. 

Academic Bio

Facundo graduated with Licenciatura in Physics from the Instituto Balseiro in the year 1998, and a Ph.D. in Computer Science in the Atanasoff Computer Science Department of Iowa State University in the year 2007, under the advise of Dr. Dimitris Margaritis and co-advise of  Dr. Vasant Honavar. In the year 2008 he starts as Assistant Professor  in the Universidad Tecnológica Nacional in Mendoza. During the years 1999 and 2000 (after graduating from Instituto Balseiro) he worked as a fellowship researcher in the Instituto de Investigaciones Cardiológicas (Institute of Heart Research) of the Medicine School of the Buenos Aires University, under the advise of Dr. Jorge Ponce-Hornos.

Publications

Marset, W. Villegas, Perez D. Sebastian, Díaz C. Ariel, & Bromberg F. (2021).  Towards practical 2D grapevine bud detection with fully convolutional networks. Computers and Electronics in Agriculture. 182, 105947.
Correa, JM. López, Todeschini M., Pérez DS., Karouta J., Bromberg F., Ribeiro A., et al. (2021).  Multi species weed detection with Retinanet one-step network in a maize field. Precision agriculture’21. 2223–2228.
Marset, W. Villegas, Pérez D. S., Díaz C. A., & Bromberg F. (2020).  Deep Learning for 2D Grapevine Bud Detection.
Ribas, A. (2019).  Exploring the Influence of Self-determination in the Collective Intelligence of Collaborative Organizations. (Bromberg, F., Ed.).IFKAD, International Forum on Knowledge Asset Dynamics.
Ribas, A., Bromberg F., & Dinamarca A. (2019).  S3LF: a Socio-Technical System for Self-Determinant Governance in Collaborative Organizations. 23RD INTERNATIONAL PUBLIC MANAGEMENT NETWORK (IPMN) CONFERENCE.
Ribas, A., & Brombereg F. (2018).  Exploring the Influence of Self-determination in the Collective Intelligence of Collaborative Organizations. Symposium on implementing collaborative governance.
Abraham, L., Bromberg F., & Forradellas R. (2018).  Ensemble of shape functions and support vector machines for the estimation of discrete arm muscle activation from external biceps 3D point clouds. Computers in Biology and Medicine. 95, 129-139.
Diaz, C. Ariel, Pérez D. Sebastián, Miatello H., & Bromberg F. (2018).  Grapevine buds detection and localization in 3D space based on Structure from Motion and 2D image classification. Computers in Industry. 99C (Special Issue on Machine Vision for Outdoor Environments), 303-312.
Diedrichs, A. Laura, Bromberg F., Dujovne D., Brun-Laguna K., & Watteyne T. (2018).  Prediction of frost events using machine learning and IoT sensing devices. IEEE Internet of Things Journal. 5(6),  4589-4597.
Abraham, L. (2018).  Visión computacional y aprendizaje de máquinas aplicado a la estimación de activación muscular del bíceps braquial. (Bromberg, F., Ed.).Universidad Nacional del Centro de la Provincia de Buenos Aires - Facultad de Ciencias Exactas. Computer Science Ph.D, 63.
Ribas, À., & Bromberg F. (2018).  Toward Self-Determinant Citizen Governance: Trust-Boosting Sociocracy 3.0 with Blockchain. Symposium on Implementing Collaborative Governance. Models, experiences and challenges to foster policy coordination, and to enhance sustainable community outcomes and public value generation.
Pérez, D. Sebastián, Bromberg F., & Diaz C. Ariel (2017).  Image classification for detection of winter grapevine buds in natural conditions using scale-invariant features transform, bag of features and support vector machines. Computers and Electronics in Agriculture. 135, 81-95.
Schlüter, F., Strappa Y., Bromberg F., & Milone D. H. (2017).  Blankets Joint Posterior score for learning Markov network structures . International Journal of Approximate Reasoning. https://doi.org/10.1016/j.ijar.2017.10.018,
Diedrichs, A. Laura, Bromberg F., Dujovne D., Brun-Laguna K., & Watteyne T. (2017).  Prediction of frost events using Bayesian networks and Random Forest. IEEE Internet of Things Journal.
Pérez, D. Sebastián, Bromberg F., & Gonzalez-Antivilo F. (2016).  Computer Vision Approach for Low Cost, High Precision Measurement of Grapevine Trunk Diameter in Outdoor Conditions.
Abraham, L., Bromberg F., & Forradellas R. (2015).  Arm muscular effort estimation from images using Computer Vision and Machine Learning. 1st International Conference on Ambient Intelligence for Health.
Edera, A., Strappa Y., & Bromberg F. (2014).  The Grow-Shrink strategy for learning Markov network structures constrained by context-specific independences. 14th edition of the Ibero-American Conference on Artificial Intelligence.
Edera, A., Schlüter F., & Bromberg F. (2014).  Learning Markov networks networks with context-specific independences.. International Journal on Artificial Intelligence Tools. 23(06), 
Abraham, L., Bromberg F., & Forradellas R. (2014).  Estimación de carga muscular mediante imágenes. Argentinean Symposium of Artificial Intelligence (ASAI) - Jornadas Argentinas de Informática. 91--98.
Schlüter, F., & Bromberg F. (2014).  El enfoque IBMAP para aprendizaje de estructuras de redes de Markov. Tesis doctoral en Facultad de Ciencias Exactas - Universidad Nacional del Centro de la Provincia de Buenos Aires. Director: Facundo Bromberg. . Doctorado en Ciencias de la Computación (PhD in Computer Science), 138.
Schlüter, F., Bromberg F., & Edera A. (2014).  The IBMAP approach for Markov network structure learning. Annals of Mathematics and Artificial Intelligence. 72(3), 197--223.
Diedrichs, A. Laura, Robles M. Inés, Bromberg F., Mercado G., & Dujovne D. (2013).  Characterization of LQI behavior in WSN for glacier area in Patagonia Argentina. Embedded Systems (SASE/CASE), 2013 Fourth Argentine Symposium and Conference on. 1--6.
Edera, A.., Schlüter F.., & Bromberg F.. (2013).  Learning Markov networks with context-specific independences. IEEE 25th International Conference on Tools with Artificial Intelligence (ICTAI).
Edera, A., Bromberg F., & Schlüter F. (2013).  Markov random fields factorization with context-specific independences.
Pérez, D. S., & Bromberg F. (2012).  Segmentación de imágenes en viñedos para la medición autónoma de variables vitícolas. XVIII Congreso Argentino de Ciencias de la Computación.
Bromberg, F., & Pérez D. S. (2012).  Interpolación Espacial Mediante Aprendizaje de Máquinas en Viñedos de la Provincia de Mendoza, Argentina.. 13th Argentine Symposium on Artificial Intelligence.
Catania, C. A., Bromberg F., & Garino C. García (2012).  An autonomous labeling approach to support vector machines algorithms for network traffic anomaly detection. Expert Systems with Applications. 39, 1822–1829.
Edera, A., & Bromberg F. (2011).  Aprendizaje de independencias específicas del contexto en Markov random fields. XVII Congreso Argentino de Ciencias de la Computación.
Bromberg, F.., Schlüter F.., & Edera A.. (2011).  Independence-based MAP for Markov networks structure discovery. 23rd IEEE International Conference on Tools with Artificial Intelligence (ICTAI).
Schlüter, F., Bromberg F., & Abraham L. (2011).  Strategies for piecing-together Local-to-Global Markov network learning algorithms. ASAI 2011.
Schlüter, F., Bromberg F., & Pérez D. S. (2010).  Speeding up the execution of a large number of statistical tests of independence. Proceedings of ASAI 2010, Argentinean Symposioum of Artificial Intelligence.
Catania, C.. A., C. Garino G., & Bromberg F.. (2010).  Application of a Bayesian semi-supervised Learning Strategy to Network Intrution Detection. Proceedings of ASAI 2010, Argentinean Symposioum of Artificial Intelligence.
Brombereg, F., Catania C. A., & Garino C. Garcia (2009).  An Autonomous labeling approach to SVM algorithms for network traffic anomaly detection. Argentine Symposium of Artificial Intelligence (ASAI). Jornadas Argentinas de Informática. Mar del Plata, Argentina..
Bromberg, F., & Schlüter F. (2009).  Variante de grow shrink para mejorar la calidad de markov blankets. XXXV Latin American Informatics Conference (CLEI), Pelotas, Brasil.
Berdún, L., & Bromberg F. (2009).  Guest Editorial: 10th Argentinean Symposium on Artificial Intelligence (ASAI 2009). Inteligencia Artificial.. 13(44), 4.
Margaritis, D., & Bromberg F. (2009).  Efficient Markov network discovery using particle filters. Computational Intelligence. 25(4), 367–394.
Bromberg, F., Margaritis D., & Honavar V. (2009).  Efficient Markov network structure discovery using independence tests. Journal of Artificial Intelligence Research. 35, 449–484.
Bromberg, F., & Margaritis D. (2009).  Improving the reliability of causal discovery from small data sets using argumentation. The Journal of Machine Learning Research. 10, 301–340.
Gandhi, P., Bromberg F., & Margaritis D. (2008).  Learning Markov Network Structure using Few Independence Tests.. SIAM Data Mining. 680--691.
Bromberg, F., & Margaritis D. (2007).  Efficient and Robust Independence-Based Markov Network Structure Discovery.. 20th International Joint Conference of Artificial Inteliigence (IJCAI). 2431-2436 .
Bromberg, F., & Margaritis D. (2007).  Markov networks structure discovery using independence tests. Computer Science. Doctor of Philosophy, 182.
Bromberg, F., Margaritis D., & Honavar V. (2006).  Efficient Markov network structure discovery using independence tests. Proceedings of the SIAM Conference in Data Mining. 141--152.

Research Proyects

a Socio-Technical System for Self-Determinant Governance
Rol: Director
Deep Learning for 2D grapevine bud detection
Rol: Director
Estimación de variables biomecánicas remota a partir de imágenes usando Computer Vision y Machine Learning
Rol: Director
Vineyard Sunlight Exposition
Rol: Director
Vineyard Sunlight Exposition
Rol: Director

Courses

Aprendizaje de máquinas
Cargo: Profesor titular
Inteligencia artificial
Cargo: Profesor titular
Reuniones de Investigacion
Cargo: Profesor titular

Grants

EIUTIME0003601TC
Rol: Director
EIUTIME0004481TC
Rol: Director
PICT-2008-0241
Rol: Director
PID-UTN-5372
Rol: Director
PID-UTN-7796
Rol: Director

Funding sources

Aprendizaje automático aplicado a problemas de Visión Computacional
UTN
Aprendizaje de redes de Markov basado en independencias
UTN
Modelado autónomo de la estructura 3D de una planta de vid a partir de imágenes 2D capturadas en condiciones naturales de campo durante el invierno
UTN
PID-UTN-7796 Hacia la toma de decisiones sociales inteligentes a partir de algoritmos para la toma de decisión secuencial en sistemas
UTN