Disclaimer against Machine learning argument ?

The proposed contents in BISE are mainly expert-based.  These contents point toward software developed by experts for specific bioimaging tasks. Other approaches could exist to help bridging bioimaging community especially in the direction of machine learning which is a more data-based approach (Meijering, E., et al 2016) . With this data-based approach, a single software can be applied to almost any data. Machine learning tools available to the bioimaging community are pointed in BISE (e.g. Sommer, C et al 2011, Marée, R. et al 2016). However, in  a data-based perspective, the reproducibility policy requires to store links to the data and annotation used in  the training stage of the machine learning process or the versions of the trained machines. Such shared machine learning metadata could constitute an interesting perspective for BISE  in bioimaging applications where machine learning will show competing performance with state-of-the-art expert-based approach (see for review Xing, F. 2017). A current limitation to the application of data-based approach is the need for annotated data which constitutes the bottleneck in machine learning. An alternative consists in automatically annotate data with help of simulators capable of generating unlimited amount of annotated data with controlled level of realism (for instance for cells Ulman, V., et al 2016). Such simulators are already pointed in BISE and will be updated with great care. Also, even in a data-based perspective it is well-known that preprocessing steps, such as normalisation, registration and denoising, are very useful and are already documented in BISE. We therefore believe that BISE will also be an extremely useful resource to the bioimaging community in the perspective of a data-based scenario.
TODO : Tagg Simulators, preprocessing,  kind of exhaustively in BIII
Sommer, C., Straehle, C., Koethe, U., & Hamprecht, F. A. (2011, March). ilastik: Interactive learning and segmentation toolkit. In Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on (pp. 230-233). IEEE.
Marée, R., Rollus, L., Stévens, B., Hoyoux, R., Louppe, G., Vandaele, R., ... & Wehenkel, L. (2016). Collaborative analysis of multi-gigapixel imaging data using Cytomine. Bioinformatics, 32(9), 1395-1401.
Meijering, E., Carpenter, A. E., Peng, H., Hamprecht, F. A., & Olivo-Marin, J. C. (2016). Imagining the future of bioimage analysis. Nature biotechnology, 34(12), 1250.
Xing, F., Xie, Y., Su, H., Liu, F., & Yang, L. (2017). Deep Learning in Microscopy Image Analysis: A Survey. IEEE Transactions on Neural Networks and Learning Systems.
Ulman, V., Svoboda, D., Nykter, M., Kozubek, M., & Ruusuvuori, P. (2016). Virtual cell imaging: A review on simulation methods employed in image cytometry. Cytometry Part A, 89(12), 1057-1072.