Algorithms force us to be explicit about what we want to achieve with decision-making. And it’s far more difficult to paper over our poorly specified or true intentions when we have to state these objectives formally.

evidence-based decision-making is only as reliable as the evidence on which it is based, and high quality examples are critically important to machine learning

From this point of view, wecan view the cost function as being afunctionalrather than just a function. Afunctional is a mapping from functions to real numbers.

Everyone who writes code on the weekends eventually thinks to themselves, You know, if things bend my way, I think I’ve got the next Facebook. Even if it’s a site that makes animated kittens dance. There’s always that little parsley sprig of hope in the mashed potatoes of your side projects.