Posts

Showing posts from January, 2017

12 - A brief introduction to Random Forests

Image
Hi crew! Today an amazing post introducing the Random Forests method is waiting for you to be read! Yep, I know, I promised this post a long time ago but seriously crew: I had no time for it! Random Forest is a machine learning method mainly used for classification and regression purposes. These kind of statistics basically learns from a training set of data and gives answers associated to new data based on what the algorithm learnt. Yep crew it sounds very similar to what Artificial Neural Networks do. In fact, also Artificial Neural Networks is a machine learning method used for regression analysis. However the two methods are based on slightly different concepts. From the historical point of view, the first concepts behind the theory of "Random Forests" are introduced for the first time by Ho in 1995 [2][3], but it is only in 2001 that they are defined as we currently know them by Breimann [1]. The algorithm itself is based on the theory of Decision Trees …

11 – 2nd TRUSS ITN Training Week!

Image
Hi crew! Here I am with another post for my blog! I hope you are all doing well, that you spent nice holidays with people you care, and that your 2017 started in the best of ways! So far, the start of 2017 was a quite busy period for me, however, lot of work causes also lots of news for you crew. Therefore  I am sorry for the delay with keep you update but because of meetings, deadlines and holidays, it was really difficult for me to write anything on the blog. My apologies crew! Last week for example I went in Barcelona. Did you know that? … No, crew it was not for holidays… It was because of work! Actually I should say that we went in Barcelona. In fact, it was the 2 nd TRUSS ITN training week organized at the Universitat Politècnica de Catalunya , and all the ESRs attended the meeting. We presented the latest achievements in our projects and it was also the opportunity to share ideas within researchers and experts. We attended many lectures focused on seismic a