Razvan Pascanu
DeepMind
About
I'm currently a Research Scientist at DeepMind and Affiliate Member at MILA. I grew up in Romania and studied computer science and electrical engineering for my undergrads in Germany. I got my MSc from Jacobs University, Bremen in 2009 under the supervision of prof. Herbert Jaeger. I hold a PhD from University of Montreal (2014), which I did under the supervision of prof. Yoshua Bengio. I was involved in developing Theano and help write some of the deep learning tutorials for Theano. I've published several papers on topics surrounding deep learning and deep reinforcement learning. I'm one of the organizers of EEML (www.eeml.eu) and part of the organizers of AIRomania. As part of the AIRomania community, I have organized RomanianAIDays since 2020, and helped build a course on AI aimed at high school students.
Research Interests
My research interests include optimization & learning (understanding how we can optimize efficiently and at scale deep models, making learning more data-efficient particularly in RL, understanding the dynamics of learning under gradient descent), memory & RNNs (how memory is formed in recurrent models and what structures can help utilize memory better), learning with multiple tasks (continual learning, transfer learning, multi-task learning, curriculum learning, meta-learning), graph neural networks (adding meaningful structure to neural networks), theory for deep networks (representation/learning), reinforcement learning, and generative models.