Short Bio

I am a research assistant at MIT and a visiting researcher at Microsoft Research. At MIT, I work with Fredo Durand and Josh Tenenbaum, where I focus on identifying cognitive biases in neural nets, and building models inspired by human visual cognition. At Microsoft I work on more general machine learning problems of sampling from distributions and it's applications. I was interning at Microsoft Research this summer, where I was supervised by Nebojsa Jojic. Before this, I was a Master's student at Harvard University where my thesis was co-supervised by Hanspeter Pfister and Fredo Durand. Before Harvard, I was at IIT Delhi back home in India :)


Apart from research, I am extremely passionate about teaching, and spend significant time writing tutorials/giving lectures in and around Boston. Click on the "Talks" or Tutorials section above for those.

Research Goal

Broadly, I am interested in the two fold problem of probing neural nets to compare their cognitive capabilities with human vision, and building models that are more inspired by human cognition. This in akin to reverse engineering human vision to solve computer vision. In graduate school, I would like to continue working along these directions.

Awards and Scholarships

  • Snapchat Research Scholarship 2018
  • Harvard SEAS Fellow (2016-2018)
  • Government of India MHRD scholarship 2014-2015

Publications

Computer Vision

  • Effects of title wording on memory of trends in line graphs[PAPER]
    Newman, A., Bylinskii, Z., Haroz, S., Madan, S., Durand, F., Oliva, A., 2018.
  • Synthetically trained icon proposals for parsing and summarizing infographics. [PAPER]
    Madan, S.*, Bylinskii, Z.*, Tancik,M.*, Zhong, K., Recasens, A.,Alsheikh, S., Pfister, H., Durand, F., 2018.
  • Understanding Infographics through Textual and Visual Tag Prediction. [PAPER]
    Madan, S.*, Bylinskii, Z.*, Alsheikh, S.*, Recasens, A.*, Zhong, K., Pfister, H., Durand, F. and Oliva, A., 2017.
  • Learning Visual Importance for Graphic Designs and Data Visualizations (Honorable Mention Award). [PAPER][CODE][WEB]
    Zoya Bylinskii, Nam Wook Kim, Peter O'Donovan, Sami Alsheikh,Madan, S., Hanspeter Pfister, Fredo Durand, Bryan Russell, Aaron Hertzmann.

Machine Learning in Biology

  • An ensemble micro neural network approach for elucidating interactions between zinc finger proteins and their target DNA. BMC Genomics, 17(13), 97 (2016). [PAPER]
    Shayoni Dutta , Spandan Madan, Harsh Parikh, Durai Sundar.
  • Exploiting the recognition code for elucidating the mechanism of zinc finger protein-DNA interactions. BMC Genomics, 17(13), 109. (2016). [PAPER]
    Shayoni Dutta , Spandan Madan, Durai Sundar.

Posters

  • Understanding Infographics through Textual and Visual Tag Prediction. NECV'17.
    Madan, S.*, Bylinskii, Z.*, Alsheikh, S.*, Recasens, A.*, Zhong, K., Pfister, H., Durand, F. and Oliva, A., 2017.

    Invited Talks

    • U.C. Berkeley vision seminar.

    • MIT graphics seminar.

    • Harvard Business School - machine learning for managers[LINK]
    • HackMIT - AI v/s Deep Learning v/s Machine Learning.
    • MIT Blueprints - an introduction to computer vision.[LINK]

    Reviewing Experience

    • One paper for TPAMI
    • Two papers for CVPR'18