Severin Perez

Archive (p. 2)

Reference: Lemmatization

August 21, 2020
Lemmatization is the process of reducing a word to its lemma (canonical form). In natural language processing, a lemmatizer may be used to reduce all words in a given text to their lemmas, which makes comparative analysis possible based on canonical forms.

Reference: Loss Function

August 21, 2020
Loss functions are used to quantify to what extent a prediction was right/wrong (rather than simply if it was right or wrong.) The purpose of a loss function is to work as part of the optimization process to update a neural network so that it reaches the desired result.

On Deep Work

March 09, 2020
In 2016, Cal Newport introduced a new term into the business lexicon: deep work. It’s an idea that has since taken hold of disaffected knowledge workers everywhere, due in no small part to the promise that they could finally start doing what they were hired to do--create value. More importantly, intertwined with this promise is something more nebulous--something fragile and fleeting. Dare we call it self-actualization?

Ditch the Daily News Habit

June 18, 2019
Much has been made of the question about what it is to be an informed citizen. We’re instructed to “read widely,” “engage in debate”, “seek out new viewpoints,” etc. The message is clear: the more information you consume, the better informed you will be. On its face, this is reasonable and well-intentioned advice. The problem is that it’s also completely wrong.

Archive (p. 2)
© Severin Perez, 2021