Suman Pal

Suman joined the Intelligent Autonomous Systems Group at TU Darmstadt as a Research Assistant on January 2021. He has won the Pioneer Fund Activator grant to found a startup focusing on robot learning from visual demonstration.

Previously, he completed his Bachelor’s in Mathematics and Computer Science at Sri Aurobindo International Centre of Education and subsequently obtained a Master’s in Advanced Robotics from Ecole Centrale de Nantes and the University of Genova. He wrote his Master’s thesis on “Deep Reinforcement Learning in Dynamic POMDP Environments” under the supervision of Joni Pajarinen, Dorothea Koert and Jan Peters.

Research Interests

Human-Robot Interaction, Computer Vision, Reinforcement Learning !!Key References # Koch, I.;Naito, K. (2007). Dimension selection for feature selection and dimension reduction with principal and independent component analysis, NEURAL COMPUTATION, 19, 2, pp.513-545, M I T PRESS.   BibTeX Reference [BibTex]

Bishop, C. M. (1999). Variational principal components, Proceedings of the Ninth International conference on Artificial Neural Networks (ICANN'99), 1, pp.509-514.   BibTeX Reference [BibTex]

Tipping, M. E.;Bishop, C. M. (1999). Mixtures of probabilistic principal component analyzers, Neural Comput, 11, 2, pp.443-82. abstracts.tcl?issn=08997667&volume=11&issu.   Download Article [PDF]   BibTeX Reference [BibTex]

Chapin, J. K.;Nicolelis, M. A. (1999). Principal component analysis of neuronal ensemble activity reveals multidimensional somatosensory representations, J Neurosci Methods, 94, 1, pp.121-40.   Download Article [PDF]   BibTeX Reference [BibTex]

Oja, E. (1982). A simplified neuron model as a principal component analyzer, Journal of Mathematical Biology, 15, pp.267-273.   BibTeX Reference [BibTex]