skip to primary navigationskip to content

Machine learning meets statistics workshop

last modified Jan 15, 2019 04:10 PM

25th and 26th March 2019, Cambridge, UK

Traditional statistical analysis and machine learning have many things in common but usually follow paths that are quite different. For prediction, traditional statistical analysis usually begins with a theory and a model and fits the parameters of the model to the data; machine learning follows a more pragmatic approach, allowing the data more freedom to prescribe the model.  Machine learning often leads to prognostic models that are more accurate but less interpretable.  For medical discovery, traditional statistical analysis usually begins by formulating a hypothesis and testing (the likelihood of) that hypothesis against the data; machine learning asks the data to formulate the (most likely) hypothesis. There are many synergies between these two disciplines and there is enormous potential in developing new fundamental theories and practical methods that transcend the boundaries of these disciplines leading to new and impactful methods to assist clinical practice and medical discovery. This workshop aims to foster such a dialogue and provide a forum for starting collaborations and for cross-fertilisation.

For more information, and to register, see: