Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Welcome to reinforcement learning


This is a funny comment, not because it's so wrong, but because of the irony. Statisticians used to complain that neural net research was just badly reproducing statistics. As late as the early 2000s, I had a stats professor actually get angry when I expressed interest in ANN theory.


Could you elaborate on that or point to any literature/websites because I'm curious to learn about what these have in common. Thank you!


The relation between ANNs and statistics is a topic over which much ink was spilled in the 1990s. This is the most concise discussion I can think of:

Sarle, Warren S. (1994). Neural Networks and Statistical Models. Proceedings of the Nineteenth Annual SAS Users Group International Conference, April, 1994.

If you want an in-depth discussion, these books relate ANNs and statistical methods:

Schürmann, Jürgen. (1996). Pattern Classification: A Unified View of Statistical and Neural Approaches.

Raudys, Sarunas. (2001). Statistical and Neural Classifiers: An Integrated Approach to Design.


Really, communities should start talking to each other.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: