I am interested in machine learning and its application to bioinformatics and computer vision. In particular, the focus of my research is on deep learning and its intersection with probabilistic graphical models and kernel methods. In the past, I have also worked on information-theoretic aspects of learning.
G. Pandey and A. Dukkipati. Learning by stretching deep networks. (Accepted) In Proceedings of Thirty-First International Conference on Machine Learning (ICML'14), 2014.
G. Pandey and A. Dukkipati. To go deep or wide in learning? In Proceedings of Seventeenth International Conference on Artificial Intelligence and Statistics (AISTATS'14), JMLR W&CP 33, 2014.
A. Dukkipati, G. Pandey, D. Ghoshdastidar, P. Koley, and D. M. V. Satya Sriram. Generative Maximum Entropy Learning for Multiclass Classification. In Proceedings of IEEE International Conference on Data Mining (ICDM'13), pp. 141-150, IEEE press, 2013.
G. Pandey and A. Dukkipati. Minimum description length principle for maximum entropy model selection. In Proceedings of IEEE International Symposium on Information Theory (ISIT'2013), pp. 1521-1525, IEEE press, 2013.
PhD student (August 2012 - ) Department of Computer Science and Automation Indian Institute of Science Bangalore-560012 CGPA - 8.0/8.0
M.E., Computer Science (August 2010 - July 2012 ) Department of Computer Science and Automation Indian Institute of Science Bangalore-560012 CGPA - 7.2/8.0
B.Tech., Computer Engineering (July 2006 - May 2010 ) Department of Computer Engineering Zakir Hussain College of Engg. and Technology, AMU Aligarh-202001 CPI - 9.5/10.0
Algorithmic Algebra Lab