Subho (Subhojeet Pramanik)

Subho (Subhojeet Pramanik)

MSc Student

RLAI, University of Alberta

" The truly unique feature of our language is not its ability to transmit information about men and lions. Rather, it’s the ability to transmit information about things that do not exist at all. As far as we know, only Sapiens can talk about entire kinds of entities that they have never seen, touched or smelled. " — Yuval Noah Harrari

Hey there, I am a MSc student at the University of Alberta working on Reinforcement Learning and Artificial Intelligence. I am currently co-supervised by Adam White and Marlos Machado; and affliated with RLAI Lab and Alberta Machine Intelligence Institute (Amii). My long term research goal is to define and understand the computational principles behind Intelligence.

My current MSc research is centered around understanding how an agent in a complex environment perceives a stream observations. In a real-world setting an agent’s immediate observation is not very informative (non Markovian), and the true-state of the world is always mammoth compared to the agent. In my research, I’m exploring how an agent can build short and long-term memories from a stream of observations which can then be used to generate an agent’s perception at a given time (an approximate Markov-state). The agent then uses its immediate perception for prediction or control.

Previously I had worked with IBM Cloud as an ML Engineer and also collaborated with IBM Research over various research projects in representation learning and Deep Learning. I’m also an avid coder, and have experience in deployment of several machine learning algorithms at scale in IBM and Kone.

Contact: spramanik [at] ualberta [dot] ca, email [at] subho [dot] in

Interests

  • Reinforcement Learning
  • Representation Learning
  • Deep Learning

Education

  • MSc in Computer Science (thesis based, Fully funded), 2021 - 2023

    University of Alberta

  • B.Tech in Computer Science and Engineering, 2015 - 2019

    Vellore Institute of Technology