"Under the random selection of a tiny subset of less than 0.1 percent of the total population, the density of the social graph of the citizens is massively reduced, while the "terrorist" cluster remains strongly interconnected."
There is no indication in the slides that the feature calculations are done on the smaller subgraph. The above comment doesn't hold if the calculations are done on the entire graph and then the 100k are sampled for training.
"Please do not put solutions to exercises online as it is important for students to work out solutions for themselves
rather than copy them from the internet"
Why exactly?
I've found that being able to walk through a solution can be quite illuminating. There's also an exploration/efficiency tradeoff. At some point you can't spend any more time thinking through a problem (because life) and being able to work through a solution still brings many (if not maximal) benefits.
I like the intent of this chart, but the Y-axis is a mess. Combining percent change from 2007 (as units for the y-axis) with roll-overs of actual numbers that contain data pre-2007 is very unintuitive.
Alessandro Lenci, Distributional models of word meaning, 2017
Doesn't appear to be release yet: http://www.annualreviews.org/doi/abs/10.1146/annurev-linguis...