%0 Conference Paper %1 10.1007/3-540-60922-9_20 %A Denis, Francois %A D'Halluin, Cyrille %A Gilleron, Rémi %B STACS 96 %C Berlin, Heidelberg %D 1996 %E Puech, Claude %E Reischuk, Rüdiger %I Springer Berlin Heidelberg %K informatik %P 231--242 %T PAC learning with simple examples %X We define a new PAC learning model. In this model, examples are drawn according to the universal distribution m(. ¦ f) of Solomomoff-Levin, where f is the target concept. The consequence is that the simple examples of the target concept have a high probability to be provided to the learning algorithm. We prove an Occam's Razor theorem. We show that the class of poly-term DNF is learnable, and the class of k-reversible languages is learnable from positive data, in this new model. %@ 978-3-540-49723-3

@inproceedings{10.1007/3-540-60922-9_20, abstract = {We define a new PAC learning model. In this model, examples are drawn according to the universal distribution m(. {\textbrokenbar} f) of Solomomoff-Levin, where f is the target concept. The consequence is that the simple examples of the target concept have a high probability to be provided to the learning algorithm. We prove an Occam's Razor theorem. We show that the class of poly-term DNF is learnable, and the class of k-reversible languages is learnable from positive data, in this new model.}, added-at = {2021-10-26T08:32:58.000+0200}, address = {Berlin, Heidelberg}, author = {Denis, Fran{\c{c}}ois and D'Halluin, Cyrille and Gilleron, R{\'e}mi}, biburl = {https://www.bibsonomy.org/bibtex/2c329dc7caf772442658bd015a9043946/mho}, booktitle = {STACS 96}, editor = {Puech, Claude and Reischuk, R{\"u}diger}, interhash = {518452d08c0f394df39f6ad9dd62a8f6}, intrahash = {c329dc7caf772442658bd015a9043946}, isbn = {978-3-540-49723-3}, keywords = {informatik}, pages = {231--242}, publisher = {Springer Berlin Heidelberg}, timestamp = {2021-10-26T08:32:58.000+0200}, title = {PAC learning with simple examples}, year = 1996 }