![]() ![]() Monte Carlo methods are a class of techniques that use random sampling to simulate a draw from some distribution. ![]() Today we’ll explore a related but perhaps even more basic concept - Monte Carlo methods. ![]() In a recent post I did an introduction to one such “foundational topic” called Markov Chains. Going back to basics can seem like a waste of time when all of the mainstream focus and attention is on sexy new stuff like self-driving cars, but I’ve found that understanding the basics at a deep level really compounds your knowledge returns over time. My own experience has been that some of these really important topics can slip through the cracks for a surprisingly long time, especially if you’re mostly self-taught like I am. These are the really foundational concepts that open the doors to all sorts of new discoveries. Then there are nodes on the interior of the graph with lots and lots of connections that lead everywhere. Some nodes sit toward the outside of the graph and have a lot of edges directed toward them - these are topics that require understanding lots of other related concepts before they can be learned. ![]() To visualize this, one can imagine a vast network of interconnected nodes. It involves continually expanding the surface area of concepts and techniques that you have at your disposal by learning new topics that build on or share a knowledge base with the topics you’ve already mastered. Learning data science is a process of exploration. This content originally appeared on Curious Insight ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |