Subscribe to DSC Newsletter

Why did you like it better than other courses? In my case, I really liked stochastic geometry. It was quite theoretical, e.g. estimating the value of Pi by throwing a needle in a rectangular grid and counting how many times the needle hit one of the lines in the grid. But it had some nice applications too. One of the problems (known as the third Grenander Problem or Exterior/Interior Problem) consisted of estimating the shape of an oil field: about 20 oil wells had been digged, and we knew which ones had oil, which ones didn't. The only assumption was that the shape of the oil field was convex. We eventually developed a fast algorithm to compute a convex domain in any dimension (when dimension = 2 or 3, the problem is easy).

As you can imagine, the issue was trying to estimate the shape / extent of oil field with as few wells as possible, as digging wells outside the field is expensive.

Views: 2781

Reply to This

Replies to This Discussion

I enjoyed Mathematical Statistics (STAT 510 and 511 at the University of Illinois) the most. It was fun to learn about important probability and almost sure convergence theorems, and the mathematical properties of various distributions.
I loved stochastic processes. And it led me to another course, which was my favorite: discrete sequence modelling. Now I'll have a last work to graduate and chose this same field. It is pretty nice the fact that I can see a way to apply stochastic and sequence models for almost anything now and amazing how easy to present and uderstand (by a customer) the results are.


On Data Science Central

© 2020   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service