Journal of Machine Learning Research

Chickering, D. M. (2002). Learning equivalence classes of Bayesian-network stractures. Journal of Machine Learning Research, 2 445-498. 

Manevitz, L. M., and Yousef, M. One-class SVMs for document classification. Journal of Machine Learning Research 2 (2001), 139-154. 

Journal of Machine Learning Research (1532-4435) Microtome Publishing. This unique journal is freely available online, and covers all aspects of machine learning. 

Pedregosa F, et al. 2011. Scikit-learn Machine Learning in Python, Journal of Machine Learning Research, 2825-2830. 

Allwein, E.L., Schapire, R.E. and Singer, Y. (2000) Redncing multiclass to binary a unifying approach for margin classifiers. Journal of Machine learning Research, 1 113-141. 

Caruana, R. and Virginia de Sa, R. (2003). Benefiting from the variables that variable selection discards. Journal of machine learning research, 3, pp. 1245-1264. 

Gabrilovich, E., and S. Markovitch. 2007. Harnessing the expertise of 70,000 human editors Knowledge-based feature generation for text categorization. Journal of Machine Learning Research 8 2297-2345. 

Journal of Machine Learning Research is an open-access journal that contains many papers on SVM, including new algorithms and SVM model optimization. All papers can be downloaded and printed for free. In the current context of widespread progress toward an open access to scientific publications, this journal has a remarkable story and is an undisputed success. 

Saul, L.K., Roweis, S. Think globally, fit locally Unsupervised learning of low dimensional manifolds. Journal of Machine Learning Research 4,119-155 (2003)... 

Kumar, S., Mohti, M., Talwalkar, A. Samping techniques for the nystrom method. Journal of Machine Learning Research 13(1), 981-1006 (2012)... 

It is worth noting that (scientific) data has intrinsic value, even if the primary purpose for which it was created, has long been fulfilled. Innovative (re-)uses of publicly available data on the internet exemplify this nicely. Scientists usually tend to produce data in the context of a specialized research project and disseminate it through the means of scientific publication in a learned journal. Once research objectives have been met or a publication has been published, scientists often lose interest in their own data as it serves no primary purpose anymore. Because of this, significant amounts of valuable scientific data either never get published and thus never become part of the knowledge commons or are rendered inaccessible to machines and thus effectively destroyed for informatics purposes. 

---