Shagun Sodhani

Hi, I am Shagun Sodhani. I am a researcher and MSc student at Montreal Institute for Learning Algorithms. I am supervised by Dr. Yoshua Bengio and Dr. Jian Tang. My research focuses on training AI systems that can interact with and learn from the physical world (reinforcement learning) and consistently improve as they do so without forgetting the previous knowledge (lifelong learning). Even a small advance in these areas would be very useful for training intelligent autonomous agents that would need to operate and make decisions over extended periods of time.

I am also interested in solving real-life problems by productizing Machine Learning (ML) and Deep Learning (DL) technologies. There are two sides to this mission statement: (i) A lot of research in ML and DL does not percolate down to products. (ii) Many real-life problems do not have a close enough research analog. Thus integrating ML and DL into products comes with several opportunities: (i) Applied research where we try to leverage the existing research work as much as possible. (ii) Fundamental research where the real-life constraints require finding a novel and innovative solution for the task at hand. Integrating cutting-edge research into products can lead to new insights and questions that are helpful for improving the original research outcome.

I graduated in Computer Science from IIT Roorkee in 2015 and worked as a Machine Learning developer with the Machine Learning team at Adobe Systems for 2 years. Research takes most of my time though I regularly attend tech-talks and meetups around the city.

I love Computer Science in general and Machine Learning in particular. I regularly read and summarise papers from these domains. I am also in interested in Maths and Economics. I always look forward to meeting interesting people and learn new stuff, both in-person and remotely. If you want to talk, feel free to drop me a line.