Abstract
AbstractOver the last few years, machine learning has revolutionized countless areas and fields. Nowadays, AI bears promise for analyzing, extracting knowledge, and driving discovery across many scientific domains such as chemistry, biology, and genomics. However, the specific challenges posed by scientific data demand to adapt machine learning techniques to new requirements. We investigate machine learning-driven scientific data analysis, focusing on a set of key requirements. These include the management of uncertainty for complex data and models, the estimation of system properties starting from low-volume and imprecise collected data, the support to scientific model development through large-scale analysis of experimental data, and the machine learning-driven integration of complementary experimental technologies.
Publisher
Springer International Publishing
Reference18 articles.
1. T. Biancalani, G. Scalia, et al., Deep Learning and Alignment of Spatially-Resolved Single Cell Transcriptomes with Tangram. Accepted for publication in Nature Methods (2021)
2. D.J. Di Bella, E. Habibi, R.R. Stickels, G. Scalia, J. Brown, P. Yadollahpour, S.M. Yang, C. Abbate, T. Biancalani, E.Z. Macosko, F. Chen, A. Regev, P. Arlotta, Molecular logic of cellular diversification in the mouse cerebral cortex. Nature (2021)
3. E. Gawehn, J.A. Hiss, G. Schneider, Deep learning in drug discovery. Mol. Informatics 35(1), 3–14 (2016)
4. I. Goodfellow, Y. Bengio, A. Courville, Deep Learning (MIT press, 2016)
5. C. Guo, G. Pleiss, Y. Sun, K.Q. Weinberger, On calibration of modern neural networks, in Proceedings of the 34th International Conference on Machine Learning, ICML’17, (2017), pp. 1321–1330
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献