More talks in the program:
15:00 - 16:00
Machine learning is all about the data. If the data set is good – in most cases, you will not need a complex algorithm to solve your problem. However, if it is not, constructing an informative feature vector can be very challenging. At least that was the case for quite a while. Some people believe that with the increasing efficiency of deep learning algorithms, feature engineering has become less important or even obsolete. Additionally, let’s not forget about the auto-ml systems that are being developed or are already in an early access stage.
Based on a case from our experience, we will compare the pros and cons of each approach, from deep learning on raw data, auto-ml, and traditional feature engineering. We’ll also try to give an honest opinion on the question raised above, "is feature engineering obsolete?"