Data assimilation is popular in numerical weather forecasting, hydrological forecasting etc. Utilizing a dynamical model distinguishes it from other forms of machine learning, image analysis, and statistical methods. This talk discussed the basic ideas of machine leaning, and compared it with machine learning. It is given after I came back from Harbin's summer school in Agust, 2017. After this talk, I began to throw myself into studying machine learning.
Check slide for more details.