Nando de Freitas
Nando de Freitas
I want to understand intelligence and harness it to extend our minds so that we can better solve challenging problems affecting us all and our environment.
I conduct research in deep learning, and associated areas including transfer learning, abstraction, reinforcement learning, multi-agents, and applications to robotics and all types of data.
I am a machine learning professor at Oxford University, a lead research scientist at Google DeepMind, and a Fellow of the Canadian Institute For Advanced Research (CIFAR) in the successful Neural Computation and Adaptive Perception program. I received my PhD from Trinity College, Cambridge University in 2000 on Bayesian methods for neural networks. From 1999 to 2001, I was a postdoctoral fellow at UC Berkeley in the AI group of Stuart Russell. I was a professor at the University of British Columbia from 2001 to 2014. I have spun off a few companies, most recently Dark Blue Labs acquired by Google. Among my recent awards are best paper awards at IJCAI 2013, ICLR 2016, ICML 2016, and the Yelp Dataset award for a multi-instance transfer learning paper at KDD 2015. I also received the 2012 Charles A. McDowell Award for Excellence in Research, and the 2010 Mathematics of Information Technology and Complex Systems (MITACS) Young Researcher Award.
- Action editor for the Journal of Machine Learning Research
- Online courses with videos: Machine Learning and Deep Learning, Monte Carlo
- Google Scholar profile
- You ca follow me on Twitter
PhD/DPhil applicants: Please follow the instructions on our admissions website.
Scott Reed and Nando de Freitas
In International Conference on Learning Representations (ICLR). 2016.
Details about Neural Programmer−Interpreters | BibTeX data for Neural Programmer−Interpreters | Link to Neural Programmer−Interpreters
Dueling Network Architectures for Deep Reinforcement Learning
Ziyu Wang‚ Nando de Freitas and Marc Lanctot
No. arXiv:1511.06581. 2015.
Details about Dueling Network Architectures for Deep Reinforcement Learning | BibTeX data for Dueling Network Architectures for Deep Reinforcement Learning | Link to Dueling Network Architectures for Deep Reinforcement Learning
From Group to Individual Labels using Deep Features
Dimitrios Kotzias‚ Misha Denil‚ Nando de Freitas and Padhraic Smyth
In ACM SIGKDD. 2015.
Details about From Group to Individual Labels using Deep Features | BibTeX data for From Group to Individual Labels using Deep Features | Download (pdf) of From Group to Individual Labels using Deep Features