The paper demonstrates that falsifiability is fundamental to learning. We
prove the following theorem for statistical learning and sequential prediction:
If a theory is falsifiable then it is learnable -- i.e. admits a strategy that
predicts optimally. An analogous result is shown for universal induction.
%0 Journal Article
%1 balduzzi2014falsifiable
%A Balduzzi, David
%D 2014
%K bounds generalization learning theory
%T Falsifiable implies Learnable
%U http://arxiv.org/abs/1408.6618
%X The paper demonstrates that falsifiability is fundamental to learning. We
prove the following theorem for statistical learning and sequential prediction:
If a theory is falsifiable then it is learnable -- i.e. admits a strategy that
predicts optimally. An analogous result is shown for universal induction.
@article{balduzzi2014falsifiable,
abstract = {The paper demonstrates that falsifiability is fundamental to learning. We
prove the following theorem for statistical learning and sequential prediction:
If a theory is falsifiable then it is learnable -- i.e. admits a strategy that
predicts optimally. An analogous result is shown for universal induction.},
added-at = {2019-08-12T18:55:24.000+0200},
author = {Balduzzi, David},
biburl = {https://www.bibsonomy.org/bibtex/20b9a1b51ee3e3c95c1ead8bec7223974/kirk86},
description = {[1408.6618] Falsifiable implies Learnable},
interhash = {dfcfe2849c808f7c58d1042e7efff8df},
intrahash = {0b9a1b51ee3e3c95c1ead8bec7223974},
keywords = {bounds generalization learning theory},
note = {cite arxiv:1408.6618},
timestamp = {2019-08-12T18:55:24.000+0200},
title = {Falsifiable implies Learnable},
url = {http://arxiv.org/abs/1408.6618},
year = 2014
}