Abstract
A high-level relation between Karl Popper’s ideas on “falsifiability of scientific theories” and the notion of “overfitting” in statistical learning theory can be easily traced. However, it was pointed out that at the level of technical details the two concepts are significantly different. One possible explanation that we suggest is that the process of falsification is an active process, whereas statistical learning theory is mainly concerned with supervised learning, which is a passive process of learning from examples arriving from a stationary distribution. We show that concepts that are closer (although still distant) to Karl Popper’s definitions of falsifiability can be found in the domain of learning using membership queries, and derive relations between Popper’s dimension, exclusion dimension, and the VCdimension.
| Original language | English |
|---|---|
| Title of host publication | Festschrift in Honor of Vladimir N. Vapnik |
| Publisher | Springer |
| Publication date | 1 Jan 2013 |
| ISBN (Electronic) | 978-3-642-41136-6 |
| Publication status | Published - 1 Jan 2013 |
| Externally published | Yes |