Tijmen Tieleman
search externally:   Google Scholar,   Springer,   CiteSeer,   Microsoft Academic Search,   Scirus ,   DBlife


I am a student of artificial intelligence, which is the study of how apparently nonintelligent things (computers) can behave apparently intelligently. I study at the university of Toronto, under Geoffrey Hinton's excellent supervision.

Research interests:

  • Neural networks (details of interest vary) - that's interesting because it's cool and it's my group's specialization.
  • The theory and practice of programming (e.g. compilers and interpreters, algorithm design, programming languagues, and programming tricks) - that's interesting because I program a lot.
  • Using artificial intelligence as a tool (as opposed to purpose) in programs - that's interesting because it's a useful tool, and sometimes it can do some of the boring work for me.

Other academic interests:

  • The study of logic and the principles of mathematics. I find this very interesting, and I've taken some excellent courses in this field.
  • Probability theory - especially its paradoxes (like the paradox of the two envelopes).


flag Using Fast Weights to Improve Persistent Contrastive Divergence
as author at  Sessions,
flag Training Restricted Boltzmann Machines using Approximations to the Likelihood Gradient
as author at  25th International Conference on Machine Learning (ICML), Helsinki 2008,